The 3dSOBS+ algorithm for moving object detection

• A novel neural-based moving object detection algorithm is proposed.
• Main novelties: initial background estimation, shadow handling, spatial coherence.
• It accurately handles moving backgrounds, gradual light variations, and shadows.
• It provides robustness against false detections for different videos.
• A deep analysis of experimental results on the BMC dataset is reported.

We propose the 3dSOBS+ algorithm, a newly designed approach for moving object detection based on a neural background model automatically generated by a self-organizing method. The algorithm is able to accurately handle scenes containing moving backgrounds, gradual illumination variations, and shadows cast by moving objects, and is robust against false detections for different types of videos taken with stationary cameras. Experimental results and comparisons conducted on the Background Models Challenge benchmark dataset demonstrate the improvements achieved by the proposed algorithm, that compares well with the state-of-the-art methods.