Extended fuzzy background modeling for moving vehicle detection using infrared vision

Chin, Yeo Boon; Soong, Lim Way; Lim, Heng Siong; Kit, Wong

doi:10.1587/elex.8.340

Cited by 7 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wei et al proposed to train a support vector machine (SVM) by combining the features of Haar and histogram of oriented gradients (HOG) to extract vehicle positions [17]. The motion-based methods mainly include the optical flow method [18] and the dynamics background modeling method [19]. Fang and Dai proposed to combine the optical flow method and Kalman filter to realize vehicle detection and tracking [20].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Liu

Zhang

2020

Journal of Sensors

View full text Add to dashboard Cite

Vehicle detection is a crucial task for autonomous driving and demands high accuracy and real-time speed. Considering that the current deep learning object detection model size is too large to be deployed on the vehicle, this paper introduces the lightweight network to modify the feature extraction layer of YOLOv3 and improve the remaining convolution structure, and the improved Lightweight YOLO network reduces the number of network parameters to a quarter. Then, the license plate is detected to calculate the actual vehicle width and the distance between the vehicles is estimated by the width. This paper proposes a detection and ranging fusion method based on two different focal length cameras to solve the problem of difficult detection and low accuracy caused by a small license plate when the distance is far away. The experimental results show that the average precision and recall of the Lightweight YOLO trained on the self-built dataset is 4.43% and 3.54% lower than YOLOv3, respectively, but the computing speed of the network decreases 49 ms per frame. The road experiments in different scenes also show that the long and short focal length camera fusion ranging method dramatically improves the accuracy and stability of ranging. The mean error of ranging results is less than 4%, and the range of stable ranging can reach 100 m. The proposed method can realize real-time vehicle detection and ranging on the on-board embedded platform Jetson Xavier, which satisfies the requirements of automatic driving environment perception.

show abstract

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Liu

Zhang

2020

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Moving average background subtraction is a commonly used technique for motion segmentation in static scenes due to its low memory requirements and ability to use knowledge of previous frames [28]. This method is robust to slight changes in the background; however, due to lack of selectivity in the updating of the background pixels, a large number of foreground pixels pollute the background in the case of low-contrast infrared imagery [29]. The Gaussian mixture model (GMM) is one of the famous background subtraction methods.…”

Section: Related Workmentioning

confidence: 99%

Moving target detection in thermal infrared imagery using spatiotemporal information

et al. 2013

View full text Add to dashboard Cite

An efficient target detection algorithm for detecting moving targets in infrared imagery using spatiotemporal information is presented. The output of the spatial processing serves as input to the temporal stage in a layered manner. The spatial information is obtained using joint space-spatial-frequency distribution and Rényi entropy. Temporal information is incorporated using background subtraction. By utilizing both spatial and temporal information, it is observed that the proposed method can achieve both high detection and a low false-alarm rate. The method is validated with experimentally generated data consisting of a variety of moving targets. Experimental results demonstrate a high value of F-measure for the proposed algorithm.

show abstract

“…In general, video-sensor data have been widely employed in automatic-surveillance applications that monitor vehicles, people, or animals [1,2,3]. Although the focus of the previous studies is mostly the surveillance accuracy, large-scale surveillance applications should also consider a real-time analysis of 24-hour video-stream data.…”

Section: Introductionmentioning

confidence: 99%

“…In general, the low-level part has a sufficient parallelism whereas the high-level part does not. For example, many video-based surveillance systems use the Gaussian mixture model (GMM) as a major technique to separate the foreground of an image from its background [1,2,3], and the GMM is a timeconsuming low-level task with a sufficient parallelism. If the GMM contributes 51% of the total workload in an intelligent-surveillance application and all of the remaining tasks are sequentially portioned, then the ideal speedup with an infinite number of processors is limited by a power of two according to Amdahl's law [9].…”

Section: Introductionmentioning

confidence: 99%

Real-time processing for intelligent-surveillance applications

Lee

Kim

et al. 2017

IEICE Electron. Express

View full text Add to dashboard Cite

Although the typical sensor-server model has been widely used in intelligent-surveillance applications, the workload increases for the centralized server as the number of sensors increases; therefore, the provision of a scalable performance requires the distribution of the centralized-server workload into the sensors. Due to the limited resources of the sensor side, however, a resource-efficient real-time processing technique is required. In this paper, a real-time sensor-side surveillance technique for which parallel processing is used on CPU-GPU hybrid-computing devices is proposed. The experiment results reveal that the proposed method can provide a real-time execution of the surveillance system.

show abstract

Extended fuzzy background modeling for moving vehicle detection using infrared vision

Cited by 7 publications

References 4 publications

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Vehicle Detection and Ranging Using Two Different Focal Length Cameras

Moving target detection in thermal infrared imagery using spatiotemporal information

Real-time processing for intelligent-surveillance applications

Contact Info

Product

Resources

About