The Arabian oryx or white oryx is a medium-sized antelope native to desert and steppe areas of the Arabian Peninsula. It was extinct in the wild by the early 1970s, but was saved in zoos and private preserves, and was reintroduced into the wild starting in 1980.
Keeping an upto date record of their population, with geotags, is an essential part of their conservation. The practice has been to count them manually by looking at a high resolution orthoimage of the sanctuary. This is error prone and time-consuming. Moreover, our customer had a backlog of such images taken over time, where the counting had to be done on all of them.
Image Credit: Declan O’Donovan, Wadi Al Safa Wildlife Centre
Fig. Orthoimage of the sanctuary (resolution: 29200×24160 pixels)
At FlytBase, we developed an image processing pipeline to automate the task of detecting oryxes in an ingested image and count them.
We started with 400 images which constituted an orthoimage and extracted 1000×600 sized images, which had either oryx in them, or oryx like objects. These were then labeled and packaged into training and testing datasets in the Pascal VOC format.
Image Credit: Declan O’Donovan, Wadi Al Safa Wildlife Centre
Fig.: Labeling Oryx and Oryx looking objects
A Faster R-CNN based object detection pipeline was set up in the cloud using the tensorflow object detection library. In the pipeline, the images were augmented by horizontally flipping and random resizing. Once everything was in place, the model was trained for 10k iterations.
The model so prepared could scan a 1000×600 sized image for Oryx. But it had to run on a high-resolution orthoimage (29200×24160 pixels). To meet that requirement, the orthoimage was split into sections sized 1000×600. Detection was executed on them, individually, and the results were stitched back. To avoid double counting or misses, the split-detect-stitch procedure was repeated with different offsets for the splits, and the median count of all the runs was obtained.
Image Credit: Declan O’Donovan, Wadi Al Safa Wildlife Centre
Fig. The high-resolution orthoimage was split into sections which could be analyzed individually by the object detection model (suggestive image)
Image Credit: Declan O’Donovan, Wadi Al Safa Wildlife Centre
Fig. A section of the orthoimage with all Oryx marked. The final count was also logged by the pipeline.
The results from this model were quite accurate and impressive. The FlytBase AI platform is able to process aerial image-data, gathered over several months, in order of minutes. This was the world’s first application of machine learning on drone image-data for Oryx detection in the desert.