Abstract:
Visual change detection is a fundamental task in computer vision and video analytics. Anomaly detection, object tracking, traffic monitoring, human-machine interaction, behavior analysis, action recognition, and visual surveillance are change detection applications. Change detection faces background fluctuations, illumination variation, weather changes, intermittent object motion, shadow, fast/slow object motion, camera motion, heterogeneous object shapes, and real-time processing. Hand-crafted features and background modelling have solved this problem traditionally. Deep learning frameworks are now used for robust change detection. This article reviews current deep learning change detection methods empirically. We specifically analyze model designs and experimental frameworks’ technical characteristics. Model design categorizes 2D-CNN, 3D-CNN, ConvLSTM, multi-scale features, residual connections, autoencoders, and GAN-based methods. An empirical analysis of deep learning evaluation settings is also presented. To our knowledge, this is the first attempt to compare deep change detection method evaluation frameworks. Finally, we discuss research needs, future directions, and our conclusions.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
