AmphibianDetector: adaptive computation for moving objects detection

TL;DR

AmphibianDetector enhances object detection by focusing on moving objects, reducing false positives and computational load, demonstrated on pedestrian datasets with accessible implementation.

Contribution

It introduces a modification to existing CNN-based detectors to selectively process moving objects, improving accuracy and efficiency with minimal changes.

Findings

Reduces false positives by focusing on moving objects.

Lowers computational requirements for detection.

Validated on CDNet2014 pedestrian dataset.

Abstract

Convolutional neural networks (CNN) allow achieving the highest accuracy for the task of object detection in images. Major challenges in further development of object detectors are false-positive detections and high demand of processing power. In this paper, we propose an approach to object detection which makes it possible to reduce the number of false-positive detections by processing only moving objects and reduce the required processing power for algorithm inference. The proposed approach is a modification of CNN already trained for object detection task. This method can be used to improve the accuracy of an existing system by applying minor changes to the algorithm. The efficiency of the proposed approach was demonstrated on the open dataset "CDNet2014 pedestrian". The implementation of the method proposed in the article is available on the GitHub: https://github.com/david-svitov/AmphibianDetector