Abstract:The growing popularity of the mini-camera is posing a serious threat to privacy and personal security. Disguised as common tools in rooms, these devices can become undetectable. Moreover, conventional active laser detection systems often fail to recognize them owing to their small lens size, weak reflectivity, and the influence of interference targets. In this paper, a method for building a laser active detection system for minicameras is proposed. Using a monostatic optical system and a deep learning classifi… Show more
“…For instance, Ke [11] designed a fully automatic camera detection and recognition system, which combines machine learning and neural network methods to identify surveillance camera equipment effectively. Liu [12] introduced a photoelectric target recognition algorithm and a detection system based on convolutional neural networks to detect indoor micro-cameras using classified networks. Huang [13] used the improved YOLOv3 model to identify micro-cameras in a single frame.…”
This paper proposes a photoelectric target detection algorithm for NVIDIA Jeston Nano embedded devices, exploiting the characteristics of active and passive differential images of lasers after denoising. An adaptive threshold segmentation method was developed based on the statistical characteristics of photoelectric target echo light intensity, which effectively improves detection of the target area. The proposed method’s effectiveness is compared and analyzed against a typical lightweight network that was knowledge-distilled by ResNet18 on target region detection tasks. Furthermore, TensorRT technology was applied to accelerate inference and deploy on hardware platforms the lightweight network Shuffv2_x0_5. The experimental results demonstrate that the developed method’s accuracy rate reaches 97.15%, the false alarm rate is 4.87%, and the detection rate can reach 29 frames per second for an image resolution of 640x480 pixels.
“…For instance, Ke [11] designed a fully automatic camera detection and recognition system, which combines machine learning and neural network methods to identify surveillance camera equipment effectively. Liu [12] introduced a photoelectric target recognition algorithm and a detection system based on convolutional neural networks to detect indoor micro-cameras using classified networks. Huang [13] used the improved YOLOv3 model to identify micro-cameras in a single frame.…”
This paper proposes a photoelectric target detection algorithm for NVIDIA Jeston Nano embedded devices, exploiting the characteristics of active and passive differential images of lasers after denoising. An adaptive threshold segmentation method was developed based on the statistical characteristics of photoelectric target echo light intensity, which effectively improves detection of the target area. The proposed method’s effectiveness is compared and analyzed against a typical lightweight network that was knowledge-distilled by ResNet18 on target region detection tasks. Furthermore, TensorRT technology was applied to accelerate inference and deploy on hardware platforms the lightweight network Shuffv2_x0_5. The experimental results demonstrate that the developed method’s accuracy rate reaches 97.15%, the false alarm rate is 4.87%, and the detection rate can reach 29 frames per second for an image resolution of 640x480 pixels.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.