Despite a relatively crowded literature about detection of power lines for aircraft safety, the works are mostly optimized with very few training images; some even use artificially generated images. The IR imaging case is even less utilized. The reason is clearly the tremendous workload to obtain real images. With this demand in mind, the authors cooperated with the Turkish Electricity Transmission Company (TEIAS) to obtain video captures from actual aircrafts. Later, the authors made a thorough inspection over the video frames to isolate, capture and clean thousands of valuable images.

In this content, 4000 IR and 4000 VL images are acquired and scaled to a size of 128x128. The IR folder contains 2000 IR images with power line and 2000 IR images with no power line. The VL folder contains 2000 VL images with power line and 2000 VL images with no power line. The IR and VL groups were deliberately constructed to contain both regular and especially confusing scenes. "TY" shows that there are no power lines in the images. "TV" shows that there are power lines in the images.

The videos were captured from 21 different regions all over Turkey at different seasonal days. Due to varying background behavior, varying temperatures and weather conditions, and varying lighting conditions, the achieved positive set contains several difficult scenes where low contrast causes close-to invisibility for power lines. The original video resolutions were 576x325 for IR and full HD for VL, however, the captured frames were scaled down to smaller sizes and the effect of resizing was tested for various image sizes. An image size of 128x128 is sufficient for a consistently accurate power line recognition.

The Vegetation Conduction Ignition Test Program was established by the Powerline Bushfire Safety Program (PBSP) as a limited duration research project. In May 2013, the PBSP sponsored a workshop of government and industry stakeholders and research institutions to identify priority research areas. Research into vegetation conduction ignition was identified as a high priority. The PBSP subsequently established the vegetation conduction ignition test program to: · Better understand bushfire ignition processes in powerline faults that involve vegetation – in particular, identify any ‘worst case’ species suitable for use in subsequent tests of powerline protection technologies; and · Create a reference data base of fault signatures for vegetation conduction faults with the aim of supporting development of improved fault detection technologies. The vegetation conduction ignition tests complement earlier test programs that studied arc-ignition, both in metal-to-metal earth faults near vegetation and in ‘wire on ground’ earth faults. In detail, the objectives of the vegetation conduction ignition test program were to: Identify the species of trees, bushes and grasses that represent the highest fire risk from electrical conduction; Identify the risk posed by smouldering material or flames due to volatile vapours produced during the conduction of electricity; Identify how this risk varies over a summer period due to the vegetation drying; Identify how this risk varies with wind speed; Record the electrical signatures of many different vegetation contacts and fire starts for future electrical signature recognition research; and Develop a list of worst case vegetation and the test conditions for use in further testing of powerline protection systems. The vegetation conditions assumed for the testing were those that exist on days of high buhshfire risk plus any variations that may be caused by other factors such as long periods of drought. A large data base of fault signature records was successfully gathered during the test program, including low-noise wide-band recordings of network voltage and vegetation fault current. The fault signature data base produced in the test program comprises about 50,000 files totalling more than 300GB of data. The 1038 tests generated a large amount of data – test logs, visible and infrared video files, low and high frequency voltage and current records, laboratory analysis records, sample collection and storage records. Usage Tips: Refer to the Vegetation Ignition Test Report appendicies A,B,C and G for further detail on the recording approach and how the MatLab charts were developed. To access the files, you should first use the Fault Signature Basic Run Sheet as a navigation tool to select a suitable test. Each .pnrf file contains all the sampled voltages and currents for a particular test. Once you have the test number, you can open the ‘Gen3i data files’ folder and open the corresponding test file using the Perception Free Viewer (available at www.hbm.com), e.g. the test file for Test 123 is file VT123.pnrf, etc. Selected samples can be exported from the viewer to an Excel spreadsheet (or other format) if required. To view the 'tdms' files (in the IND data folder) you will need to download LabView (or a similar software) - (available at www.ni.com/download-labview) If you would like to discuss this data with the PBSP, please email fault.signature@ecodev.vic.gov.au