An Embedded Computer-Vision System for Multi-Object Detection in Traffic Surveillance

Mhalla, Ala; Chateau, Thierry; Gazzah, Sami; Amara, Najoua Essoukri Ben

doi:10.1109/tits.2018.2876614

Cited by 70 publications

(30 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial resolution was 720 × 576 pixels. Since the original dataset featured some misdetections [ 1 ], the proper labels were manually added. The overall set of videos included 2105 detections for training and 593 detections for testing.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

T-RexNet—A Hardware-Aware Neural Network for Real-Time Detection of Small Moving Objects

Canepa

Ragusa

Zunino

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper presents the T-RexNet approach to detect small moving objects in videos by using a deep neural network. T-RexNet combines the advantages of Single-Shot-Detectors with a specific feature-extraction network, thus overcoming the known shortcomings of Single-Shot-Detectors in detecting small objects. The deep convolutional neural network includes two parallel paths: the first path processes both the original picture, in gray-scale format, and differences between consecutive frames; in the second path, differences between a set of three consecutive frames is only handled. As compared with generic object detectors, the method limits the depth of the convolutional network to make it less sensible to high-level features and easier to train on small objects. The simple, Hardware-efficient architecture attains its highest accuracy in the presence of videos with static framing. Deploying our architecture on the NVIDIA Jetson Nano edge-device shows its suitability to embedded systems. To prove the effectiveness and general applicability of the approach, real-world tests assessed the method performances in different scenarios, namely, aerial surveillance with the WPAFB 2009 dataset, civilian surveillance using the Chinese University of Hong Kong (CUHK) Square dataset, and fast tennis-ball tracking, involving a custom dataset. Experimental results prove that T-RexNet is a valid, general solution to detect small moving objects, which outperforms in this task generic existing object-detection approaches. The method also compares favourably with application-specific approaches in terms of the accuracy vs. speed trade-off.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The recent growth of industrial applications for object detection stimulates the research community toward novel solutions. Intelligent video analysis is the core of several industry applications such as transportation [ 1 ], sentiment analysis [ 2 ], and sport [ 3 , 4 ].…”

Section: Introductionmentioning

confidence: 99%

T-RexNet—A Hardware-Aware Neural Network for Real-Time Detection of Small Moving Objects

Canepa

Ragusa

Zunino

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…They first employed background subtraction model to remove identified moving vehicles, and then utilized Faster R-CNN [10] to detect remaining anomalous vehicles. Mhalla [7] et al introduced a modified Faster R-CNN (MF R-CNN) for vehicle detection and pedestrian detection, they removed the fourth Max-Pooling layer, and replaced the remaining Max-Pooling layers by Stochastic-Pooling layers in original Faster R-CNN. Finally, they made an embedded system for intelligent traffic surveillance.…”

Section: The Related Workmentioning

confidence: 99%

“…Although cameras have been deployed on most urban roads, humans cannot review every monitor at the same time, and humans are unable to focus on monitors all the time. Therefore, a friendly intelligent traffic surveillance system is needed to help humans achieve intelligent traffic management [6] [7]. The first task of intelligent traffic surveillance is accurate vehicle detection [6].…”

Section: Introductionmentioning

confidence: 99%

A Robust Vehicle Detection Scheme for Intelligent Traffic Surveillance Systems in Smart Cities

et al. 2020

View full text Add to dashboard Cite

Accurately obtaining road vehicle information is important in intelligent traffic surveillance systems for smart cities. Especially smart vehicle detection is recognized as the critical research issue of intelligent traffic surveillance systems. In this paper, a robust real-time vehicle detection method for the system is proposed. The method combines background subtraction model MOG2(Mixture of Gaussians) with a modified SqueezeNet model (H-SqueezeNet). The MOG2 model is utilized to create scale-insensitive Region of Interest (RoIs) from video frames. H-SqueezeNet is then proposed to accurately identify vehicle category. The effectiveness of the method was verified in CDnet2014 dataset, UA-DETRAC dataset and video data from a traffic intersection in Suzhou, China. The experiment results show that the method can achieves excellent detection accuracy in traffic surveillance systems, and achieve an average detection speed of 39.1 FPS.

show abstract

“…The main intention is to improve autonomy and resolve robotic challenges while engaging in a salient object discovery process. The embedded computer-vision system in traffic surveillance was introduced by Mhalla et al [16] for multi-object detection. This method, which is used for detecting traffic objects in traffic scenarios, consists of a robust detector that makes use of a generic deep detector and enhances detection accuracy.…”

Section: Related Workmentioning

confidence: 99%

A two-level computer vision-based information processing method for improving the performance of human–machine interaction-aided applications

Alfarraj

Tolba

2020

Complex Intell. Syst.

View full text Add to dashboard Cite

The computer vision (CV) paradigm is introduced to improve the computational and processing system efficiencies through visual inputs. These visual inputs are processed using sophisticated techniques for improving the reliability of human–machine interactions (HMIs). The processing of visual inputs requires multi-level data computations for achieving application-specific reliability. Therefore, in this paper, a two-level visual information processing (2LVIP) method is introduced to meet the reliability requirements of HMI applications. The 2LVIP method is used for handling both structured and unstructured data through classification learning to extract the maximum gain from the inputs. The introduced method identifies the gain-related features on its first level and optimizes the features to improve information gain. In the second level, the error is reduced through a regression process to stabilize the precision to meet the HMI application demands. The two levels are interoperable and fully connected to achieve better gain and precision through the reduction in information processing errors. The analysis results show that the proposed method achieves 9.42% higher information gain and a 6.51% smaller error under different classification instances compared with conventional methods.

show abstract

An Embedded Computer-Vision System for Multi-Object Detection in Traffic Surveillance

Cited by 70 publications

References 36 publications

T-RexNet—A Hardware-Aware Neural Network for Real-Time Detection of Small Moving Objects

T-RexNet—A Hardware-Aware Neural Network for Real-Time Detection of Small Moving Objects

A Robust Vehicle Detection Scheme for Intelligent Traffic Surveillance Systems in Smart Cities

A two-level computer vision-based information processing method for improving the performance of human–machine interaction-aided applications

Contact Info

Product

Resources

About