Fish detection in complex background using machine learning

Object detection using Faster-RCNN in Google Colab

After labelling more than thousand images of fish in the videos with complex backgrounds, uneven lighting and turbid water, I trained a faster-RCNN model using the object detection API and then tested the frozen model on video recordings using OpenCV. The results? Pretty solid detection of both fish in most frames of the recording.

Avatar
Vishwanath Varma
Post-Doctoral Fellow

My research interests include behavioural variation, circadian rhythms and social cognition.

Related