This is an open source object detection model by TensorFlow in TensorFlow Lite format. While it is not recommended to use this model in production surveys, it can be useful for demonstration purposes and to get started with smart assistants in ArcGIS Survey123. You are responsible for the use of this model. When using Survey123, it is your responsibility to review and manually correct outputs.This object detection model was trained using the Common Objects in Context (COCO) dataset. COCO is a large-scale object detection dataset that is available for use under the Creative Commons Attribution 4.0 License.The dataset contains 80 object categories and 1.5 million object instances that include people, animals, food items, vehicles, and household items. For a complete list of common objects this model can detect, see Classes.The model can be used in ArcGIS Survey123 to detect common objects in photos that are captured with the Survey123 field app. Using the modelFollow the guide to use the model. You can use this model to detect or redact common objects in images captured with the Survey123 field app. The model must be configured for a survey in Survey123 Connect.Fine-tuning the modelThis model cannot be fine-tuned using ArcGIS tools.InputCamera feed (either low-resolution preview or high-resolution capture).OutputImage with common object detections written to its EXIF metadata or an image with detected objects redacted.Model architectureThis is an open source object detection model by TensorFlow in TensorFlow Lite format with MobileNet architecture. The model is available for use under the Apache License 2.0.Sample resultsHere are a few results from the model.

The MR3 site, located near the Roman city of Mustis in Northern Tunisia (36°20'29.69"N, 9°7'59.47"E), was chosen as the case study for this project. This medium-sized rural settlement was identified during the AFRIPAL reconnaissance, a Polish-Tunisian project led by Tomasz Waliszewski (Faculty of Archaeology, University of Warsaw) and Jamel Hajji (L’Institut national du patrimoine).

As a newly discovered site, MR3 is not yet protected by local heritage institutions, making it vulnerable to looting, uncontrolled development, and agricultural activities. The urgency to document and preserve this site digitally was a primary motivator for this project. Documenting the MR3 site provides critical insights into the rural settlement dynamics during the Roman and Byzantine periods in Tunisia, and how they continued to function in Early Islamic and Medieval periods.

This project, founded by DARIAH Workflow THEME aimed to not only document the current state of the site but also to create a detailed workflow for using MobileGIS in archaeological prospection. The workflow developed through this project will serve as a model for other archaeologists facing similar challenges, ensuring rapid and thorough documentation of threatened archaeological sites.

The data set represents the results of the case study survey. It consist of:

Presentation of the Projects results, which was shown on DARIAH 2024 ANNUAL CONFERENCE MR3.mpkx - ArcGIS Pro project; a GIS project of the whole MR3 site MR3 Survey results as csv MR3 Survey results as kmz XLSX file that contains formated question for MobileGIS Survey123 app, possibile to upload to Survey Connect MR3 Survey123 app questions in more readable format A full GIS data base with results of the survey. The reuslts of the survey is also avialable: https://arcg.is/1yGyzH and as online map https://arcg.is/1TnXDn0

The project "MobileGIS workflow in archaeological prospection: the case study of a rural site near the Roman city of Mustis (N Tunisia)" was founded by DARIAH Workflow THEME .

The Eklutna River is an anadromous river in South Central Alaska, whose salmon runs have provided important subsistence fishing for Native Alaskan's for millennia. US Fish and Wildlife Service and our partners at the Native Village of Eklutna are hoping to better document the locations of returning fish and the behaviors they are exhibiting during fall river surveys. Spawning behaviors, fish condition, and species are recorded along with a time and georeferenced point on the map. This survey will also help manage photos and data in a tidy structure. Making this query-able through ArcGIS Online will allow for easy data management and up to date sharing between USFWS and NVE. This template includes all XLSForm features supported in ArcGIS Survey123 and was created in Survey123 Connect.

The Eklutna River is an anadromous river in South Central Alaska, whose salmon runs have provided important subsistence fishing for Native Alaskan's for millennia. US Fish and Wildlife Service and our partners at the Native Village of Eklutna are hoping to better document the locations of returning fish and the behaviors they are exhibiting during fall river surveys. Spawning behaviors, fish condition, and species are recorded along with a time and georeferenced point on the map. This survey will also help manage photos and data in a tidy structure. Making this query-able through ArcGIS Online will allow for easy data management and up to date sharing between USFWS and NVE. This template includes all XLSForm features supported in ArcGIS Survey123 and was created in Survey123 Connect.