Exploring visual techniques for indoor intrusion detection using detectron2 and Faster RCNN

Abstract

As societal evolution marches forward, there's an escalating emphasis on indoor security concerns. Within the safety realm, indoor intrusion detection emerges as a pivotal challenge, given its direct implications on safeguarding human lives and assets. Leveraging visual methods for indoor intrusion detection holds promising potential, particularly due to its straightforward deployment advantages. This study zeroes in on surveillance video footage, a prevalent medium in the security domain, as its experimental muse. Post an initial preprocessing phase utilizing a video difference map, the research introduces a pedestrian detection algorithm hinged on the synergy of detectron2 and Faster R-CNN. Insights gleaned reveal that this combined algorithm, when augmented with the video difference map preprocessing, exhibits commendable accuracy, robustness, and real-time efficacy on surveillance footage, especially in scenarios bereft of significant target occlusion. Moreover, this algorithm showcases an adeptness at discerning diminutively sized targets, demonstrating resilience against varying light magnitudes and maintaining impeccable accuracy amidst intricate lighting conditions. By harnessing this methodology, the enhancement of indoor environment safety monitoring becomes feasible, thereby bolstering the provision of dependable protection for individuals.