Here are a few use cases for this project:

1. Construction Site Safety Monitoring: The "yolov7 for ppe detection" model can be used in construction sites to ensure that all workers are wearing the necessary personal protective equipment (PPE). The model can alert safety officers when someone is detected without proper PPE.

2. Factory Compliance Checking: Manufacturers can use this computer vision model to ensure all factory workers are complying with PPE rules. The model can detect workers not wearing necessary equipment, providing evidence for potential OSHA violations.

3. Training Simulations: The model can be employed in virtual reality or augmented reality for training simulations. Here, trainees would be alerted whenever they fail to "wear" appropriate PPE in the simulation, teaching them the importance of safety procedures.

4. Emergency Situations Analysis: In disaster response or accident investigation, it can be used to assess if rescue and emergency medical teams followed safety protocols by wearing the correct PPE, by analyzing photos or video footage.

5. Insurances and Litigations: The CV model could prove invaluable in personal injury cases, where it can be used to establish, via media evidence, whether a worker was wearing proper PPE at the time of an accident, potentially affecting compensations or liability claims.

For my thesis, I need to recognize keyboards in an image. I got 615 images of keyboards from internet search engines and personal devices, split those into train-val-test (70:20:10) and augmented the train ones into 20k images. A simplified and resized version for YOLOv7 training can be found here. For my next task of recognizing keys on the keyboard I use Characters detection dataset.

Unmanned aerial vehicles (UAVs) have become increasingly popular in recent years for both commercial and recreational purposes. Regrettably, the security of people and infrastructure is also clearly threatened by this increased demand. To address the current security challenge, much research has been carried out and several innovations have been made. Many faults still exist, however, including type or range detection failures and the mistaken identification of other airborne objects (for example, birds). A standard dataset that contains photos of drones and birds and on which the model might be trained for greater accuracy is needed to conduct experiments in this field. The supplied dataset is crucial since it will help train the model, giving it the ability to learn more accurately and make better decisions. The dataset that is being presented is comprised of a diverse range of images of birds and drones in motion. Pexel website's images and videos have been used to construct the dataset. Images were obtained from the frames of the recordings that were acquired, after which they were segmented and augmented with a range of circumstances. This would improve the machine-learning model's detection accuracy while increasing dataset training. The dataset has been formatted according to the YOLOv7 PyTorch specification. The test, train, and valid folders are contained within the given dataset. These folders each feature a plaintext file that corresponds to an associated image. Relevant metadata regarding the discovered object is described in the plaintext file. Images and labels are the two subfolders that constitute the folders. The collection consists of 20,925 images of birds and drones. The images have a 640 x 640 pixel resolution and are stored in JPEG format.

Subset from MaskedFace Net

PREPROCESSING Auto-Orient: Applied Resize: Stretch to 416x416

AUGMENTATIONS Outputs per training example: 3 Flip: Horizontal, Vertical Shear: ±15° Horizontal, ±15° Vertical Noise: Up to 5% of pixels Cutout: 3 boxes with 10% size each Bounding Box: Blur: Up to 10px Bounding Box: Noise: Up to 5% of pixels

Efficient and precise thinning during the orchard blossom period is a crucial factor in enhancing both fruit yield and quality. The accurate recognition of inflorescence is the cornerstone of intelligent blossom equipment. To advance the process of intelligent blossom thinning, this paper addresses the issue of suboptimal performance of current inflorescence recognition algorithms in detecting dense inflorescence at a long distance. It introduces an inflorescence recognition algorithm, YOLOv7-E, based on the YOLOv7 neural network model. YOLOv7 incorporates an efficient multi-scale attention mechanism (EMA) to enable cross-channel feature interaction through parallel processing strategies, thereby maximizing the retention of pixel-level features and positional information on the feature maps. Additionally, the SPPCSPC module is optimized to preserve target area features as much as possible under different receptive fields, and the Soft-NMS algorithm is employed to reduce the likelihood of missing detections in overlapping regions. The model is trained on a diverse dataset collected from real-world field settings. Upon validation, the improved YOLOv7-E object detection algorithm achieves an average precision and recall of 91.4% and 89.8%, respectively, in inflorescence detection under various time periods, distances, and weather conditions. The detection time for a single image is 80.9 ms, and the model size is 37.6 Mb. In comparison to the original YOLOv7 algorithm, it boasts a 4.9% increase in detection accuracy and a 5.3% improvement in recall rate, with a mere 1.8% increase in model parameters. The YOLOv7-E object detection algorithm presented in this study enables precise inflorescence detection and localization across an entire tree at varying distances, offering robust technical support for differentiated and precise blossom thinning operations by thinning machinery in the future.

Custom Multi-Altitude Aerial Vehicles Dataset:

Created for publishing results for ICUAS 2023 paper "How High can you Detect? Improved accuracy and efficiency at varying altitudes for Aerial Vehicle Detection", following the abstract of the paper.

Abstract—Object detection in aerial images is a challenging task mainly because of two factors, the objects of interest being really small, e.g. people or vehicles, making them indistinguishable from the background; and the features of objects being quite different at various altitudes. Especially, when utilizing Unmanned Aerial Vehicles (UAVs) to capture footage, the need for increased altitude to capture a larger field of view is quite high. In this paper, we investigate how to find the best solution for detecting vehicles in various altitudes, while utilizing a single CNN model. The conditions for choosing the best solution are the following; higher accuracy for most of the altitudes and real-time processing ( > 20 Frames per second (FPS) ) on an Nvidia Jetson Xavier NX embedded device. We collected footage of moving vehicles from altitudes of 50-500 meters with a 50-meter interval, including a roundabout and rooftop objects as noise for high altitude challenges. Then, a YoloV7 model was trained on each dataset of each altitude along with a dataset including all the images from all the altitudes. Finally, by conducting several training and evaluation experiments and image resizes we have chosen the best method of training objects on multiple altitudes to be the mixup dataset with all the altitudes, trained on a higher image size resolution, and then performing the detection using a smaller image resize to reduce the inference performance. The main results

The creation of a custom dataset was necessary for altitude evaluation as no other datasets were available. To fulfill the requirements, the footage was captured using a small UAV hovering above a roundabout near the University of Cyprus campus, where several structures and buildings with solar panels and water tanks were visible at varying altitudes. The data were captured during a sunny day, ensuring bright and shadowless images. Images were extracted from the footage, and all data were annotated with a single class labeled as 'Car'. The dataset covered altitudes ranging from 50 to 500 meters with a 50-meter step, and all images were kept at their original high resolution of 3840x2160, presenting challenges for object detection. The data were split into 3 sets for training, validation, and testing, with the number of vehicles increasing as altitude increased, which was expected due to the larger field of view of the camera. Each folder consists of an aerial vehicle dataset captured at the corresponding altitude. For each altitude, the dataset annotations are generated in YOLO, COCO, and VOC formats. The dataset consists of the following images and detection objects:

    Data
    Subset
    Images
    Cars


    50m
    Train
    130
    269


    50m
    Test
    32
    66


    50m
    Valid
    33
    73


    100m
    Train
    246
    937


    100m
    Test
    61
    226


    100m
    Valid
    62
    250


    150m
    Train
    244
    1691


    150m
    Test
    61
    453


    150m
    Valid
    61
    426


    200m
    Train
    246
    1753


    200m
    Test
    61
    445


    200m
    Valid
    62
    424


    250m
    Train
    245
    3326


    250m
    Test
    61
    821


    250m
    Valid
    61
    823


    300m
    Train
    246
    6250


    300m
    Test
    61
    1553


    300m
    Valid
    62
    1585


    350m
    Train
    246
    10741


    350m
    Test
    61
    2591


    350m
    Valid
    62
    2687


    400m
    Train
    245
    20072


    400m
    Test
    61
    4974


    400m
    Valid
    61
    4924


    450m
    Train
    246
    31794


    450m
    Test
    61
    7887


    450m
    Valid
    61
    7880


    500m
    Train
    270
    49782


    500m
    Test
    67
    12426


    500m
    Valid
    68
    12541


    mix_alt
    Train
    2364
    126615


    mix_alt
    Test
    587
    31442


    mix_alt
    Valid
    593
    31613

It is advised to further enhance the dataset so that random augmentations are probabilistically applied to each image prior to adding it to the batch for training. Specifically, there are a number of possible transformations such as geometric (rotations, translations, horizontal axis mirroring, cropping, and zooming), as well as image manipulations (illumination changes, color shifting, blurring, sharpening, and shadowing).

Context This dataset is related to previously published public dataset "Sonar-to-RGB Image Translation for Diver Monitoring in Poor Visibility Environments". https://zenodo.org/records/7728089 It contains ZED-right camera and sonar images collected from Hemmoor Lake and DFKI Maritime Exploration Hall. Sensors: Low Frq (1.2MHz) Blueprint Oculus M1200d Sonar and ZED Right Camera Content The dataset is created for Diver Detection and Diver Tracking applications. For the Diver Detection part, the dataset is prepared to train, validate and test YOLOv7 model. 7095 images are used for training data, and 3095 images are used for validation data. These sets are augmented from originally captured and sampled ZED camera images. Augmentation methods are not applied to the Test data, which contains 822 images. Train and validation contain images from both the DFKI pool and Hemmor Lake, while the test data is only collected from the lake. To distinguish between the original image and the augmented image, check the name coding. Naming of object detection images: original_image_name.jpg if augmented: original_image_name_

Here are a few use cases for this project:

1. Traffic Management Systems: The "Spit Bridge Cones" model can be used to detect cones and markers on roads or construction sites, providing real-time data for improving traffic flow and maintaining safety standards.

2. Drone Navigation: Drones could use this model to identify marked cones on terrain during aerial mapping or surveying, making flight navigation more accurate and reliable.

3. Autonomous Vehicles: This model can be employed by autonomous driving solutions to recognize and react to cones and markers on the road, improving their ability to navigate safely.

4. Road Maintenance Detection: Authorities and road management teams can use the model to identify cones that mark road hazards or maintenance work, providing important information for planning road repair operations.

5. AR Games Development: Developers of augmented reality driving- or navigation-based games could use the "Spit Bridge Cones" model to map real-world cone locations into the game environment for enhanced realism.

Accurate identification of small tea buds is a key technology for tea harvesting robots, which directly affects tea quality and yield. However, due to the complexity of the tea plantation environment and the diversity of tea buds, accurate identification remains an enormous challenge. Current methods based on traditional image processing and machine learning fail to effectively extract subtle features and morphology of small tea buds, resulting in low accuracy and robustness. To achieve accurate identification, this paper proposes a small object detection algorithm called STF-YOLO (Small Target Detection with Swin Transformer and Focused YOLO), which integrates the Swin Transformer module and the YOLOv8 network to improve the detection ability of small objects. The Swin Transformer module extracts visual features based on a self-attention mechanism, which captures global and local context information of small objects to enhance feature representation. The YOLOv8 network is an object detector based on deep convolutional neural networks, offering high speed and precision. Based on the YOLOv8 network, modules including Focus and Depthwise Convolution are introduced to reduce computation and parameters, increase receptive field and feature channels, and improve feature fusion and transmission. Additionally, the Wise Intersection over Union loss is utilized to optimize the network. Experiments conducted on a self-created dataset of tea buds demonstrate that the STF-YOLO model achieves outstanding results, with an accuracy of 91.5% and a mean Average Precision of 89.4%. These results are significantly better than other detectors. Results show that, compared to mainstream algorithms (YOLOv8, YOLOv7, YOLOv5, and YOLOx), the model improves accuracy and F1 score by 5-20.22 percentage points and 0.03-0.13, respectively, proving its effectiveness in enhancing small object detection performance. This research provides technical means for the accurate identification of small tea buds in complex environments and offers insights into small object detection. Future research can further optimize model structures and parameters for more scenarios and tasks, as well as explore data augmentation and model fusion methods to improve generalization ability and robustness.

YOLO-based Segmented Dataset for Drone vs. Bird Detection for Deep and Machine Learning Algorithms

Unmanned aerial vehicles (UAVs), or drones, have witnessed a sharp rise in both commercial and recreational use, but this surge has brought about significant security concerns. Drones, when misidentified or undetected, can pose risks to people, infrastructure, and air traffic, especially when confused with other airborne objects, such as birds. To overcome this challenge, accurate detection systems are essential. However, a reliable dataset for distinguishing between drones and birds has been lacking, hindering the progress of effective models in this field.

This dataset is designed to fill this gap, enabling the development and fine-tuning of models to better identify drones and birds in various environments. The dataset comprises a diverse collection of images, sourced from Pexel’s website, representing birds and drones in motion. These images were captured from video frames and are segmented, augmented, and pre-processed to simulate different environmental conditions, enhancing the model's training process.

Formatted in accordance with the YOLOv7 PyTorch specification, the dataset is organized into three folders: Test, Train, and Valid. Each folder contains two sub-folders—*Images* and Labels—with the Labels folder including the associated metadata in plaintext format. This metadata provides valuable information about the detected objects within each image, allowing the model to accurately learn and detect drones and birds in varying circumstances. The dataset contains a total of 20,925 images, all with a resolution of 640 x 640 pixels in JPEG format, providing comprehensive training and validation opportunities for machine learning models.

• Test Folder: Contains 889 images (both drone and bird images). The folder has sub-categories marked as BT (Bird Test Images) and DT (Drone Test Images).

• Train Folder: With a total of 18,323 images, this folder includes both drone and bird images, also categorized as BT and DT.

• Valid Folder: Consisting of 1,740 images, the images in this folder are similarly categorized into BT and DT.

This dataset is essential for training more accurate models that can differentiate between drones and birds in real-time applications, thereby improving the reliability of drone detection systems for enhanced security and efficiency.

https://github.com/siromermer/CS2-CSGO-Yolov8-Yolov7-ObjectDetection

1. ct_body
2. ct_head
3. t_body
4. t_head

in .yaml file there are 5 classes , but actual class number is 4 . When annotating images i mistakenly give blank space in classes.txt file and because of that there is empty class which is 0 in this case , but it wont create any problem , i just wanted to inform kaggle users . Dataset is little bit small for now , but as soos as possible i will increase image number for sure

Traditional manual inspection approaches face challenges due to the reliance on the experience and alertness of operators, which limits their ability to meet the growing demands for efficiency and precision in modern manufacturing processes. Deep learning techniques, particularly in object detection, have shown significant promise for various applications. This paper proposes an improved YOLOv11-based method for surface defect detection in electronic products, aiming to address the limitations of existing YOLO models in handling complex backgrounds and small target defects. By introducing the MD-C2F module, DualConv module, and Inner_MPDIoU loss function, the improved YOLOv11 model has achieved significant improvements in precision, recall rate, detection speed, and other aspects. The improved YOLOv11 model demonstrates notable improvements in performance, with a precision increase from 90.9% to 93.1%, and a recall rate improvement from 77.0% to 84.6%. Furthermore, it shows a 4.6% rise in mAP50, from 84.0% to 88.6%. When compared to earlier YOLO versions such as YOLOv7, YOLOv8, and YOLOv9, the improved YOLOv11 achieves a significantly higher precision of 89.3% in resistor detection, surpassing YOLOv7’s 54.3% and YOLOv9’s 88.0%. In detecting defects like LED lights and capacitors, the improved YOLOv11 reaches mAP50 values of 77.8% and 85.3%, respectively, both outperforming the other models. Additionally, in the generalization tests conducted on the PKU-Market-PCB dataset, the model’s detection accuracy improved from 91.4% to 94.6%, recall from 82.2% to 91.2%, and mAP50 from 91.8% to 95.4%.These findings emphasize that the proposed YOLOv11 model successfully tackles the challenges of detecting small defects in complex backgrounds and across varying scales. It significantly enhances detection accuracy, recall, and generalization ability, offering a dependable automated solution for defect detection in electronic product manufacturing.

Traditional manual inspection approaches face challenges due to the reliance on the experience and alertness of operators, which limits their ability to meet the growing demands for efficiency and precision in modern manufacturing processes. Deep learning techniques, particularly in object detection, have shown significant promise for various applications. This paper proposes an improved YOLOv11-based method for surface defect detection in electronic products, aiming to address the limitations of existing YOLO models in handling complex backgrounds and small target defects. By introducing the MD-C2F module, DualConv module, and Inner_MPDIoU loss function, the improved YOLOv11 model has achieved significant improvements in precision, recall rate, detection speed, and other aspects. The improved YOLOv11 model demonstrates notable improvements in performance, with a precision increase from 90.9% to 93.1%, and a recall rate improvement from 77.0% to 84.6%. Furthermore, it shows a 4.6% rise in mAP50, from 84.0% to 88.6%. When compared to earlier YOLO versions such as YOLOv7, YOLOv8, and YOLOv9, the improved YOLOv11 achieves a significantly higher precision of 89.3% in resistor detection, surpassing YOLOv7’s 54.3% and YOLOv9’s 88.0%. In detecting defects like LED lights and capacitors, the improved YOLOv11 reaches mAP50 values of 77.8% and 85.3%, respectively, both outperforming the other models. Additionally, in the generalization tests conducted on the PKU-Market-PCB dataset, the model’s detection accuracy improved from 91.4% to 94.6%, recall from 82.2% to 91.2%, and mAP50 from 91.8% to 95.4%.These findings emphasize that the proposed YOLOv11 model successfully tackles the challenges of detecting small defects in complex backgrounds and across varying scales. It significantly enhances detection accuracy, recall, and generalization ability, offering a dependable automated solution for defect detection in electronic product manufacturing.

Traditional manual inspection approaches face challenges due to the reliance on the experience and alertness of operators, which limits their ability to meet the growing demands for efficiency and precision in modern manufacturing processes. Deep learning techniques, particularly in object detection, have shown significant promise for various applications. This paper proposes an improved YOLOv11-based method for surface defect detection in electronic products, aiming to address the limitations of existing YOLO models in handling complex backgrounds and small target defects. By introducing the MD-C2F module, DualConv module, and Inner_MPDIoU loss function, the improved YOLOv11 model has achieved significant improvements in precision, recall rate, detection speed, and other aspects. The improved YOLOv11 model demonstrates notable improvements in performance, with a precision increase from 90.9% to 93.1%, and a recall rate improvement from 77.0% to 84.6%. Furthermore, it shows a 4.6% rise in mAP50, from 84.0% to 88.6%. When compared to earlier YOLO versions such as YOLOv7, YOLOv8, and YOLOv9, the improved YOLOv11 achieves a significantly higher precision of 89.3% in resistor detection, surpassing YOLOv7’s 54.3% and YOLOv9’s 88.0%. In detecting defects like LED lights and capacitors, the improved YOLOv11 reaches mAP50 values of 77.8% and 85.3%, respectively, both outperforming the other models. Additionally, in the generalization tests conducted on the PKU-Market-PCB dataset, the model’s detection accuracy improved from 91.4% to 94.6%, recall from 82.2% to 91.2%, and mAP50 from 91.8% to 95.4%.These findings emphasize that the proposed YOLOv11 model successfully tackles the challenges of detecting small defects in complex backgrounds and across varying scales. It significantly enhances detection accuracy, recall, and generalization ability, offering a dependable automated solution for defect detection in electronic product manufacturing.

Traditional manual inspection approaches face challenges due to the reliance on the experience and alertness of operators, which limits their ability to meet the growing demands for efficiency and precision in modern manufacturing processes. Deep learning techniques, particularly in object detection, have shown significant promise for various applications. This paper proposes an improved YOLOv11-based method for surface defect detection in electronic products, aiming to address the limitations of existing YOLO models in handling complex backgrounds and small target defects. By introducing the MD-C2F module, DualConv module, and Inner_MPDIoU loss function, the improved YOLOv11 model has achieved significant improvements in precision, recall rate, detection speed, and other aspects. The improved YOLOv11 model demonstrates notable improvements in performance, with a precision increase from 90.9% to 93.1%, and a recall rate improvement from 77.0% to 84.6%. Furthermore, it shows a 4.6% rise in mAP50, from 84.0% to 88.6%. When compared to earlier YOLO versions such as YOLOv7, YOLOv8, and YOLOv9, the improved YOLOv11 achieves a significantly higher precision of 89.3% in resistor detection, surpassing YOLOv7’s 54.3% and YOLOv9’s 88.0%. In detecting defects like LED lights and capacitors, the improved YOLOv11 reaches mAP50 values of 77.8% and 85.3%, respectively, both outperforming the other models. Additionally, in the generalization tests conducted on the PKU-Market-PCB dataset, the model’s detection accuracy improved from 91.4% to 94.6%, recall from 82.2% to 91.2%, and mAP50 from 91.8% to 95.4%.These findings emphasize that the proposed YOLOv11 model successfully tackles the challenges of detecting small defects in complex backgrounds and across varying scales. It significantly enhances detection accuracy, recall, and generalization ability, offering a dependable automated solution for defect detection in electronic product manufacturing.

Regular monitoring of the number of various fish species in a variety of habitats is essential for marine conservation efforts and marine biology research. To address the shortcomings of existing manual underwater video fish sampling methods, a plethora of computer-based techniques are proposed. However, there is no perfect approach for the automated identification and categorizing of fish species. This is primarily due to the difficulties inherent in capturing underwater videos, such as ambient changes in luminance, fish camouflage, dynamic environments, watercolor, poor resolution, shape variation of moving fish, and tiny differences between certain fish species. This study has proposed a novel Fish Detection Network (FD_Net) for the detection of nine different types of fish species using a camera-captured image that is based on the improved YOLOv7 algorithm by exchanging Darknet53 for MobileNetv3 and depthwise separable convolution for 3 x 3 filter size in the augmented feature extraction network bottleneck attention module (BNAM). The mean average precision (mAP) is 14.29% higher than it was in the initial version of YOLOv7. The network that is utilized in the method for the extraction of features is an improved version of DenseNet-169, and the loss function is an Arcface Loss. Widening the receptive field and improving the capability of feature extraction are achieved by incorporating dilated convolution into the dense block, removing the max-pooling layer from the trunk, and incorporating the BNAM into the dense block of the DenseNet-169 neural network. The results of several experiments comparisons and ablation experiments demonstrate that our proposed FD_Net has a higher detection mAP than YOLOv3, YOLOv3-TL, YOLOv3-BL, YOLOv4, YOLOv5, Faster-RCNN, and the most recent YOLOv7 model, and is more accurate for target fish species detection tasks in complex environments.