Vehicle Behavior Analysis Using Target Motion Trajectories

Song, Huansheng; Lu, Sheng-Nan; Ma, Xiang; Yang, Yuan; Liu, Xueqin; Zhang, Peng

doi:10.1109/tvt.2014.2307958

Cited by 41 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the data of the projected image can be projected onto the inverse projection plane to obtain an inverse projection map, which copies the spatial information of the inverse projection plane. The inverse projection [5] process consists of two parts: the design of the inverse projection plane and the construction of the inverse projection map. The proposed method relies on the space information with three dimensions; therefore, the calibration procedure for traffic scenes is necessary, and there are many calibration methods for traffic scenes.…”

Section: Inverse Projection Plane and Inverse Projection Mapmentioning

confidence: 99%

“…These feature descriptors are combined with classification algorithms for vehicle monitoring systems in ITSs, such as artificial neural networks, support vector machines, AdaBoost, and sparse representation classification. In the method based on moving features [4,5], the entire or part of the vehicle is tracked, and the corresponding tracking trajectories used to detect vehicle targets and analyze vehicle behaviors are obtained.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Image Processing and Three‐Dimensional Data Reconstruction Algorithm Based on Traffic Video in Vehicle Component Detection

Song

Wang

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Vehicle detection is one of the important technologies in intelligent video surveillance systems. Owing to the perspective projection imaging principle of cameras, traditional two-dimensional (2D) images usually distort the size and shape of vehicles. In order to solve these problems, the traffic scene calibration and inverse projection construction methods are used to project the threedimensional (3D) information onto the 2D images. In addition, a vehicle target can be characterized by several components, and thus vehicle detection can be fulfilled based on the combination of these components. The key characteristics of vehicle targets are distinct during a single day; for example, the headlight brightness is more significant at night, while the vehicle taillight and license plate color are much more prominent in the daytime. In this paper, by using the background subtraction method and Gaussian mixture model, we can realize the accurate detection of target lights at night. In the daytime, however, the detection of the license plate and taillight of a vehicle can be fulfilled by exploiting the background subtraction method and the Markov random field, based on the spatial geometry relation between the corresponding components. Further, by utilizing Kalman filters to follow the vehicle tracks, detection accuracy can be further improved. Finally, experiment results demonstrate the effectiveness of the proposed methods.

show abstract

Section: Inverse Projection Plane and Inverse Projection Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Image Processing and Three‐Dimensional Data Reconstruction Algorithm Based on Traffic Video in Vehicle Component Detection

Song

Wang

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The first baseline we use is the KLT tracker [15], which has been consistently used in applications such as Action Recognition [37,17,18,38], Vehicle Tracking [33,35,8], 3D Reconstruction [1,5,25] in recent literature and is still the state-of-the-art even though it was proposed in 1981, suggesting it's effectiveness on a variety of applications. As explained in Section 1, KLT may fail to track points on the object boundaries effectively as it uses the whole patch, which may not remain stable at the object boundaries.…”

Section: The Klt Trackermentioning

confidence: 99%

“…Next, we evaluate our algorithm on the vehicle tracking problem. Point tracking has been applied extensively for this application [14,23,25,29,33,35], where KLT [15] is the most common choice [33,35,32,23,25]. Vehicle tracking has become increasingly important with the impending advent of autonomous vehicles, traffic surveillance systems, with conventional feature point-based approaches in order to make the systems more robust.…”

Section: Vehicle Trackingmentioning

confidence: 99%

“…Feature Point Detection, Matching and Tracking is an important problem that has been studied extensively in the Computer Vision literature and has numerous applications such as Mosaicing, Object Tracking [33,35,8], Action Recognition [37,17,18,38] and Structure-from-Motion [1,5,25] among others. The Kanade-Lukas-Tomasi (KLT) [15,36,30] tracker is still the most widely used tracker in the literature even after 30 years due to its robustness and speed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CoMaL Tracking: Tracking Points at the Object Boundaries

Ramakrishnan

Ravindran

Mittal

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Traditional point tracking algorithms such as the KLT use local 2D information aggregation for feature detection and tracking, due to which their performance degrades at the object boundaries that separate multiple objects. Recently, CoMaL Features have been proposed that handle such a case. However, they proposed a simple tracking framework where the points are re-detected in each frame and matched. This is inefficient and may also lose many points that are not re-detected in the next frame. We propose a novel tracking algorithm to accurately and efficiently track CoMaL points. For this, the level line segment associated with the CoMaL points is matched to MSER segments in the next frame using shape-based matching and the matches are further filtered using texture-based matching. Experiments show improvements over a simple redetect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries.

show abstract