Motion detection using binocular image flow in dynamic scenes

Min, Qi

doi:10.1186/s13634-016-0349-8

Cited by 7 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [3], the quotient of the optical flow and the depth obtained from stereovision was used as constraint for a robust and powerful detection scheme. In [4], moving obstacles were detected from the difference between the mixed flow and the ego-motion flow by integrating stereovision and optical flow. The works in [5,6,7] also developed stereovision systems for autonomous vehicles or robots to enable real-time obstacle avoidance.…”

Section: Introductionmentioning

confidence: 99%

Obstacle and Free Space Detection Based on U-V-Disparity

Chen¹,

Ye²,

Hu³

et al. 2017

dtetr

View full text Add to dashboard Cite

This paper presents a novel method for obstacle and free space detection for intelligent vehicles by using U-V-disparity of stereovision. The U-V-disparity map is generated by calculating the histogram of the disparities with regards to the row and column. The obstacles and road surface appear as various straight lines in the U-V-disparity maps. By detecting these lines and reconstructing them back to the initial disparity map, obstacles can be located and measured. The free space is extracted from the subtraction of the obstacle disparity map obtained from the U-disparity from the initial dense disparity map. The experimental results show that the proposed methods can efficiently detect obstacle and free space.

show abstract

Section: Introductionmentioning

confidence: 99%

Obstacle and Free Space Detection Based on U-V-Disparity

Chen¹,

Ye²,

Hu³

et al. 2017

dtetr

View full text Add to dashboard Cite

show abstract

“…The point set obtained by the above methods unavoidably contains many moving points when a large area of image is composed of moving objects. To achieve true static feature points, Reference [16,17] proposed that only feature points on the ground surface were selected for ego-motion estimation. However, the methods are comparatively poor in adaptability to the environment because a plenty number of effective ground feature points are hard to be extracted in some situations.…”

Section: Introductionmentioning

confidence: 99%

A Robust Method for Ego-Motion Estimation in Urban Environment Using Stereo Camera

2016

Sensors

Self Cite

View full text Add to dashboard Cite

Visual odometry estimates the ego-motion of an agent (e.g., vehicle and robot) using image information and is a key component for autonomous vehicles and robotics. This paper proposes a robust and precise method for estimating the 6-DoF ego-motion, using a stereo rig with optical flow analysis. An objective function fitted with a set of feature points is created by establishing the mathematical relationship between optical flow, depth and camera ego-motion parameters through the camera’s 3-dimensional motion and planar imaging model. Accordingly, the six motion parameters are computed by minimizing the objective function, using the iterative Levenberg–Marquard method. One of key points for visual odometry is that the feature points selected for the computation should contain inliers as much as possible. In this work, the feature points and their optical flows are initially detected by using the Kanade–Lucas–Tomasi (KLT) algorithm. A circle matching is followed to remove the outliers caused by the mismatching of the KLT algorithm. A space position constraint is imposed to filter out the moving points from the point set detected by the KLT algorithm. The Random Sample Consensus (RANSAC) algorithm is employed to further refine the feature point set, i.e., to eliminate the effects of outliers. The remaining points are tracked to estimate the ego-motion parameters in the subsequent frames. The approach presented here is tested on real traffic videos and the results prove the robustness and precision of the method.

show abstract

“…based on motion structure analysis to improve the system robustness. There are some researches presenting their robust method in specific scenes (Musleh et al, 2012a;Min et al, 2016a) or using other sensors (He et al, 2015a). Musleh et al (2012a) presented an inliers selection scheme in urban situations that only the feature points on the ground will be chosen to estimate the motion.…”

Section: Introductionmentioning

confidence: 99%

A Robust Method for Stereo Visual Odometry Based on Multiple Euclidean Distance Constraint and Ransac Algorithm

Zhou

Tong

Liu

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Commission III, WG III/2 KEY WORDS: Visual Odometry, Stereo Vision, Robot Navigation, RANSAC Algorithm ABSTRACT:Visual Odometry (VO) is a critical component for planetary robot navigation and safety. It estimates the ego-motion using stereo images frame by frame. Feature points extraction and matching is one of the key steps for robotic motion estimation which largely influences the precision and robustness. In this work, we choose the Oriented FAST and Rotated BRIEF (ORB) features by considering both accuracy and speed issues. For more robustness in challenging environment e.g., rough terrain or planetary surface, this paper presents a robust outliers elimination method based on Euclidean Distance Constraint (EDC) and Random Sample Consensus (RANSAC) algorithm. In the matching process, a set of ORB feature points are extracted from the current left and right synchronous images and the Brute Force (BF) matcher is used to find the correspondences between the two images for the Space Intersection. Then the EDC and RANSAC algorithms are carried out to eliminate mismatches whose distances are beyond a predefined threshold. Similarly, when the left image of the next time matches the feature points with the current left images, the EDC and RANSAC are iteratively performed. After the above mentioned, there are exceptional remaining mismatched points in some cases, for which the third time RANSAC is applied to eliminate the effects of those outliers in the estimation of the ego-motion parameters (Interior Orientation and Exterior Orientation). The proposed approach has been tested on a real-world vehicle dataset and the result benefits from its high robustness.

show abstract

Motion detection using binocular image flow in dynamic scenes

Cited by 7 publications

References 24 publications

Obstacle and Free Space Detection Based on U-V-Disparity

Obstacle and Free Space Detection Based on U-V-Disparity

A Robust Method for Ego-Motion Estimation in Urban Environment Using Stereo Camera

A Robust Method for Stereo Visual Odometry Based on Multiple Euclidean Distance Constraint and Ransac Algorithm

Contact Info

Product

Resources

About