Home > Business > Handgun detection using combined human pose and weapon appearance

Handgun detection using combined human pose and weapon appearance

wallpapers Business 2020-11-06 >

CCTV cameras are nowadays omnipresent. They can be used for the detection of security threats. For instance, detecting handguns in RGB photos taken by video surveillance cameras can be a more versatile and economic option than X-ray scanning machines. A recent study suggests a way to detect firearms using both the appearance of an object and human pose estimation.

Image credit: James Case via Wikimedia (CC BY 2.0)

Firstly, the information of the human pose is extracted. Then, the hand regions for each detected person are inferred. Finally, a convolutional neural network is used to classify hand regions into gun and no-gun areas. The results show that the pose estimation improves the detection accuracy as the object cannot sometimes be viewed due to occlusion, poor lighting conditions, or camera distance. Also, while analyzing only hand regions, false positives in other places are avoided. The suggested approach outperforms currently employed gun detection techniques.

CCTV surveillance systems are essential nowadays to prevent and mitigate security threats or dangerous situations such as mass shootings or terrorist attacks, in which early detection is crucial. These solutions are manually supervised by a security operator, which has significant limitations. Novel deep learning-based methods have allowed to develop automatic and real time weapon detectors with promising results. However, these approaches are based on visual weapon appearance only and no additional contextual information is exploited. For handguns, body pose may be a useful cue, especially in cases where the gun is barely visible and also as a way to reduce false positives. In this work, a novel method is proposed to combine in a single architecture both weapon appearance and 2D human pose information. First, pose keypoints are estimated to extract hand regions and generate binary pose images, which are the model inputs. Then, each input is processed with a different subnetwork to extract two feature maps. Finally, this information is combined to produce the hand region prediction (handgun vs no-handgun). A new dataset composed of samples collected from different sources has been used to evaluate model performance under different situations. Moreover, the robustness of the model to different brightness and weapon size conditions (simulating conditions in which appearance is degraded by low light and distance to the camera) have also been tested. Results obtained show that the combined model improves overall performance substantially with respect to appearance alone as used by other popular methods such as YOLOv3.


MIS-ASIA is an online content marketing platform that has a large number of visitors worldwide. It is considered to be the leading IT, mechanical, chemical, and nanomaterial information distributor in the Asia-Pacific region. The MIS-ASIA website provides high-quality articles and news on digital information technology, mechanical technology, nanotechnology, biology and science for scientists, engineers and industry experts, machinery suppliers and buyers, chemical suppliers and laboratories. If you need advertising and posting service, or you need to start sponsorship, please contact us.
Say something
  • All comments(0)
    No comment yet. Please say something!