AmphibianDetector: adaptive computation for moving objects detection
This work addresses object detection challenges for applications like surveillance or autonomous systems, but it is incremental as it modifies existing CNNs with minor changes.
The paper tackles the problem of false-positive detections and high processing power in object detection by proposing a method that processes only moving objects, reducing false positives and computational demand. It demonstrates efficiency on the CDNet2014 pedestrian dataset, though no specific numerical results are provided.
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