Optical flow and active contour for moving object segmentation and detection in monocular robot

Liu, P.R.; Meng, Max Q.-H.; Liu, P.X.; Tong, F.F.L.; Wang, Xiaona

doi:10.1109/robot.2006.1642328

Cited by 11 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is the corresponding Bhattacharrya factor. According to equation (2) and (3), we can get the weights update formula based on color histogram as:…”

Section: Weights Update Based On Color Histogram Featurementioning

confidence: 99%

“…This paper mainly showed the following three characteristics: (1). Introduced the quadrature pruning factor m θ in to the QKF, and optimized the restructuring of the integration points, using a pruning QKF to produce the optimal proposal distribution function, well overcome the particle degradation, and effectively improve the filtering accuracy; (2). Using the color characteristics and motion edge features as observation model to calculate the filter particles weights; (3).…”

Section: C Onclusionmentioning

confidence: 99%

“…Moving target tracking problem is a more difficult field of computer vision in complex environment. In recent years, many algorithms were proposed, which mainly based on motion model [1], optical flow [2], feature [3], image area information [4], and so on. The feature-based method is easy and robust.…”

Section: Introductionmentioning

confidence: 99%

“…At present, Particle filter (PF) is the main algorithm in researching object tracking, and get rapid development in this field [2][3][4][5][6]. The reason is that it can represent any form of probability distribution in theory.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-feature Fusion Tracking Based on A New Particle Filter

Li¹,

Cao²,

Wu³

2012

JCP

View full text Add to dashboard Cite

A new kind of particle filter is proposed for the state estimation of nonlinear system. The proposed algorithm based on Quadrature Kalman Filter by using integral pruning factor, which optimizes and reorganizes the integration point. New algorithm overcomes the particle degeneration phenomenon well by using Pruning Quadrature Kalman Filter to produce optimized proposal distribution function. In the improving particle filter framework, using color and motion edge character as observation model. Fusing feature weights through the D-S evidence theory, and effectively avoid the questions of bad robust produced by the single color feature in the illumination of mutation, posture change and similar feature occlusion. Experiment results indicate that the proposed method is more robust to track object and has good performance in complex scene.

show abstract

“…is the corresponding Bhattacharrya factor. According to equation (2) and (3), we can get the weights update formula based on color histogram as:…”

Section: Weights Update Based On Color Histogram Featurementioning

confidence: 99%

Section: C Onclusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-feature Fusion Tracking Based on A New Particle Filter

Li¹,

Cao²,

Wu³

2012

JCP

View full text Add to dashboard Cite

show abstract

“…Third, the predicted segmentation results on blurred and rotated images can hardly be guaranteed to be accurate enough. To solve this problem, the multi-view geometry [16] and optical flow [17,18] methods are often introduced to jointly distinguish dynamic outliers. Multi-view geometry finds outliers by calculating projection errors of feature points on different frames.…”

Section: Introductionmentioning

confidence: 99%

A real-time semantic visual SLAM for dynamic environment based on deep learning and dynamic probabilistic propagation

Chen

Ling

Gao

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Most existing visual simultaneous localization and mapping (SLAM) algorithms rely heavily on the static world assumption. Combined with deep learning, semantic SLAM has become a popular solution for dynamic scenes. However, most semantic SLAM methods show poor real-time performance when dealing with dynamic scenes. To handle this problem, a real-time semantic SLAM method is proposed in this paper, combining knowledge distillation and dynamic probability propagation strategy. First, to improve the execution speed, a multi-level knowledge distillation method is adopted to obtain a lightweight segmentation model, which is more suitable for continuous frames to create an independent semantic segmentation thread. This segmentation thread only accepts keyframes as input so that the system can avoid time delay caused by processing each frame. Second, a static semantic keyframe selection strategy is proposed based on the segmentation results. In this way, those keyframes containing more static information will be selected to reduce the participation of dynamic objects. By combining segmentation results and data matching algorithm, our system can realize the update and propagation of dynamic probability, reducing the influence of dynamic points in the pose optimization process. Validation results based on the KITTI and TUM datasets show that our method can effectively deal with dynamic feature points and improve running speed simultaneously.

show abstract

Motion Estimation for Objects Analysis and Detection in Videos

Favorskaya

2012

Advances in Reasoning-Based Image Processing Intelligent Systems

View full text Add to dashboard Cite

Optical flow and active contour for moving object segmentation and detection in monocular robot

Cited by 11 publications

References 8 publications

Multi-feature Fusion Tracking Based on A New Particle Filter

Multi-feature Fusion Tracking Based on A New Particle Filter

A real-time semantic visual SLAM for dynamic environment based on deep learning and dynamic probabilistic propagation

Motion Estimation for Objects Analysis and Detection in Videos

Contact Info

Product

Resources

About