Cumulative frame differencing for urban vehicle detection

Al-Smadi, Ma’moun; Abdulrahim, Khairi; Salam, Rosalina Abdul

doi:10.1117/12.2242959

Cited by 9 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The background must be modelled accurately, with frequent updates to consider changes in the background, such as changes in lighting conditions, scene geometry or moving objects (e.g., trees shaken by the wind) [38]. Background subtraction methods can be categorised into parametric, nonparametric or predictive techniques [39].…”

Section: Motion Detection Methods Based On Background Modellingmentioning

confidence: 99%

“…Optical flow refers to the flow vectors of moving objects, and it indicates the speed of movement of pixels in subsequent frames. It indicates the velocity and the direction of pixel movements [39,50]. Han et al [51] combined optical flow with three-frame differencing to detect moving objects.…”

Section: Other Motion Detection Methodsmentioning

confidence: 99%

“…Cumulative frame differencing (CFD), which involves the summation of successive frame differencing, of presented by Alsmadi et al [39] to improve the detection of slow-moving vehicles. Firstly, the successive frame differences are accumulated to generate cumulative frame difference (CFD).…”

Section: Other Motion Detection Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features

Algethami

Redfern

2020

J. Imaging

View full text Add to dashboard Cite

We propose a tracking-by-detection algorithm to track the movements of meeting participants from an overhead camera. An advantage of using overhead cameras is that all objects can typically be seen clearly, with little occlusion; however, detecting people from a wide-angle overhead view also poses challenges such as people’s appearance significantly changing due to their position in the wide-angle image, and generally from a lack of strong image features. Our experimental datasets do not include empty meeting rooms, and this means that standard motion based detection techniques (e.g., background subtraction or consecutive frame differencing) struggle since there is no prior knowledge for a background model. Additionally, standard techniques may perform poorly when there is a wide range of movement behaviours (e.g. periods of no movement and periods of fast movement), as is often the case in meetings. Our algorithm uses a novel coarse-to-fine detection and tracking approach, combining motion detection using adaptive accumulated frame differencing (AAFD) with Shi-Tomasi corner detection. We present quantitative and qualitative evaluation which demonstrates the robustness of our method to track people in environments where object features are not clear and have similar colour to the background. We show that our approach achieves excellent performance in terms of the multiple object tracking accuracy (MOTA) metrics, and that it is particularly robust to initialisation differences when compared with baseline and state of the art trackers. Using the Online Tracking Benchmark (OTB) videos we also demonstrate that our tracker is very strong in the presence of background clutter, deformation and illumination variation.

show abstract

Section: Motion Detection Methods Based On Background Modellingmentioning

confidence: 99%

Section: Other Motion Detection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features

Algethami

Redfern

2020

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Many research activities focus on pedestrian detection and recognition. Most of them utilize either motion segmentation combined with template matching or descriptive feature extraction followed by machine learning like support vector machine [3], [4]. Pedestrian recognition using color histogram matching was discussed in [5], by extracting color histograms from three horizontal partitions of the human image.…”

Section: Introductionmentioning

confidence: 99%

Automated Pedestrian Recognition Based on Deep Convolutional Neural Networks

Al-Hazaimeh¹,

Al-Smadi²

2019

IJMLC

Self Cite

View full text Add to dashboard Cite

“…This approach helps reduce computational complexity without compromising on the quality of difference images. Al-Smadi et al (2016) used a dynamic threshold value to estimate the global variance of the motion-accumulated variations of pixel intensity, based on the standard deviation of cumulative frame differencing (CFD). Radzi et al (2014) proposed a technique to extract moving objects based on temporal differencing, ghost removal and shadow removal using normalized cross correlation (NCC) while using a non-static Pan-Tilt-Zoom (PTZ) camera.…”

Section: Introductionmentioning

confidence: 99%

Real-time detection of moving objects in a video sequence by using data fusion algorithm

Tang

Zhang

et al. 2018

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The moving object detection and tracking technology has been widely deployed in visual surveillance for security, which is, however, an extremely challenge to achieve real-time performance owing to environmental noise, background complexity and illumination variation. This paper proposes a novel data fusion approach to attack this problem, which combines an entropy-based Canny (EC) operator with the local and global optical flow (LGOF) method, namely EC-LGOF. Its operation contains four steps. The EC operator firstly computes the contour of moving objects in a video sequence, and the LGOF method then establishes the motion vector field. Thirdly, the minimum error threshold selection (METS) method is employed to distinguish the moving object from the background. Finally, edge information fuses temporal information concerning the optic flow to label the moving objects. Experiments are conducted and the results are given to show the feasibility and effectiveness of the proposed method.

show abstract

Cumulative frame differencing for urban vehicle detection

Cited by 9 publications

References 0 publications

A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features

A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features

Automated Pedestrian Recognition Based on Deep Convolutional Neural Networks

Real-time detection of moving objects in a video sequence by using data fusion algorithm

Contact Info

Product

Resources

About