Deep multi-level feature pyramids: Application for non-canonical firearm detection in video surveillance

Lim, Jun Yi; Jobayer, Istiaque Al; Baskaran, Vishnu Monn; Lim, Joanne; See, John; Wong, KokSheik

doi:10.1016/j.engappai.2020.104094

Cited by 29 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, 300 images of size 512x512 were obtained from the publicly available Monash Guns Dataset [31] for test purposes. These images show different CCTV scenarios with people holding handguns in several body poses.…”

Section: Figure 1: Sample Images From Gun Movies Databasementioning

confidence: 99%

See 1 more Smart Citation

Handgun Detection Using Combined Human Pose and Weapon Appearance

et al. 2021

View full text Add to dashboard Cite

Closed-circuit television (CCTV) systems are essential nowadays to prevent security threats or dangerous situations, in which early detection is crucial. Novel deep learning-based methods have allowed to develop automatic weapon detectors with promising results. However, these approaches are mainly based on visual weapon appearance only. For handguns, body pose may be a useful cue, especially in cases where the gun is barely visible. In this work, a novel method is proposed to combine, in a single architecture, both weapon appearance and 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 in different subnetworks and combined to produce the handgun bounding box. Results obtained show that the combined model improves the handgun detection state of the art, achieving from 4.23 to 18.9 AP points more than the best previous approach. INDEX TERMSCCTV surveillance, deep learning, handgun detection, human pose estimation.

show abstract

Section: Figure 1: Sample Images From Gun Movies Databasementioning

confidence: 99%

“…For the last experiment, the realistic Monash Guns Dataset [31] has been used to test the methods compared in this work. This dataset shows people holding handguns in a variety of real-world CCTV surveillance environments.…”

Section: Test Set B -Monash Datasetmentioning

confidence: 99%

Handgun Detection Using Combined Human Pose and Weapon Appearance

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Authors in [Lim et al 2021] provide a new dataset (Monash Guns Dataset), taking into consideration some design tips from ImageNet dataset and MS COCO and aiming to mix images of weapons in canonical and non-canonical situations. After the creation of the dataset, they trained a multi-level multi-scale object detector implemented by M2Det.…”

Section: Dataset Improvement For Object Detectionmentioning

confidence: 99%

“…Considering the problem of detecting guns in video surveillance cameras, we intended to use a training dataset as close as possible to images found on images from security videos. The Monash Guns Dataset [Lim et al 2021] has weapons in a representative way and also with a variety of different guns. Authors describe the dataset as a mixture of canonical and non-canonical images of guns recorded similar to video surveillance cameras.…”

Section: Datasetsmentioning

confidence: 99%

Detection of weapon possession and fire in Public Safety surveillance cameras

Moura¹,

Gondim²,

Claro³

et al. 2021

Anais Do XVIII Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2021)

View full text Add to dashboard Cite

The employment of video surveillance cameras by public safety agencies enables incident detection in monitored cities by using object detection for scene description, enhancing the protection to the general public. Object detection has its drawbacks, such as false positives. Our work aims to enhance object detection and image classification by employing IoU (Intersection over Union) to minimize the false positives and identify weapon holders or fire in a frame, adding more information to the scene.

show abstract

“…All the works on weapon detection in videos apply one of the most influential single-image object detection models such as Faster R-CNN [22], SSD [14], YOLO [21], Efficientdet [24] or NAS-FPN [9]. The first studies in this context improved the detection in videos by building new datasets [17,10,27,12,11]. The most recent studies applied preor post-processing techniques to further reducing the errors [16,26,4,19].…”

Section: Introductionmentioning

confidence: 99%

MULTICAST: MULTI Confirmation-level Alarm SysTem based on CNN and LSTM to mitigate false alarms for handgun detection in video-surveillance

Olmos,

Tabik,

Perez-Hernandez

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite the constant advances in computer vision, integrating modern single-image detectors in real-time handgun alarm systems in video-surveillance is still debatable. Using such detectors still implies a high number of false alarms and false negatives. In this context, most existent studies select one of the latest single-image detectors and train it on a better dataset or use some preprocessing, post-processing or data-fusion approach to further reduce false alarms. However, none of these works tried to exploit the temporal information present in the videos to mitigate false detections. This paper presents a new system, called MULTI Confirmation-level Alarm SysTem based on Convolutional Neural Networks (CNN) and Long Short Term Memory networks (LSTM) (MULTI-CAST), that leverages not only the spacial information but also the temporal information existent in the videos for a more reliable handgun detection. MULTICAST consists of three stages, i) a handgun detection stage, ii) a CNN-based spacial confirmation stage and iii) LSTM-based temporal confirmation stage. The temporal confirmation stage uses the positions of the detected handgun in previous instants to predict its trajectory in the next frame. Our experiments show that MULTI-CAST reduces by 80% the number of false alarms with respect to Faster R-CNN based-single-image detector, which makes it more useful in providing more effective and rapid security responses.

show abstract

Deep multi-level feature pyramids: Application for non-canonical firearm detection in video surveillance

Cited by 29 publications

References 23 publications

Handgun Detection Using Combined Human Pose and Weapon Appearance

Handgun Detection Using Combined Human Pose and Weapon Appearance

Detection of weapon possession and fire in Public Safety surveillance cameras

MULTICAST: MULTI Confirmation-level Alarm SysTem based on CNN and LSTM to mitigate false alarms for handgun detection in video-surveillance

Contact Info

Product

Resources

About