Detecting Suspicious Behavior: How to Deal with Visual Similarity through Neural Networks
This work addresses security and surveillance challenges by reducing false positives in behavior detection, though it appears incremental as it builds on existing neural network methods.
The paper tackled the problem of detecting suspicious behavior in surveillance videos, where high visual similarity between normal and suspicious samples leads to high false-positive rates, and achieved improved detection performance by implementing and optimizing 3D Convolutional Neural Networks with different training approaches.
Suspicious behavior is likely to threaten security, assets, life, or freedom. This behavior has no particular pattern, which complicates the tasks to detect it and define it. Even for human observers, it is complex to spot suspicious behavior in surveillance videos. Some proposals to tackle abnormal and suspicious behavior-related problems are available in the literature. However, they usually suffer from high false-positive rates due to different classes with high visual similarity. The Pre-Crime Behavior method removes information related to a crime commission to focus on suspicious behavior before the crime happens. The resulting samples from different types of crime have a high-visual similarity with normal-behavior samples. To address this problem, we implemented 3D Convolutional Neural Networks and trained them under different approaches. Also, we tested different values in the number-of-filter parameter to optimize computational resources. Finally, the comparison between the performance using different training approaches shows the best option to improve the suspicious behavior detection on surveillance videos.