Real-Time Feature Matching using Adaptive and Spatially Distributed Classification Trees

Boffy, Aurélien; Tsin, Yanghai; Genç, Yakup

doi:10.5244/c.20.55

Cited by 10 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A good survey about different model-based tracking approaches can be found in [11,21]. Some authors propose the use of machine learning techniques to solve the problem of wide baseline keypoint matching [3,15]. Supervised classification systems requires a pre-processing, where a system is trained with a determined set of known examples (training set) that represents variations in all their independent variables.…”

Section: Tracking By Detectionmentioning

confidence: 99%

Real-time optical markerless tracking for augmented reality applications

Barandiarán

Paloc

Graña

2009

J Real-Time Image Proc

View full text Add to dashboard Cite

Augmented reality (AR) technology consists in adding computer-generated information (2D/3D) to a real video sequence in such a manner that the real and virtual objects appear coexisting in the same world. To get a realistic illusion, the real and virtual objects must be properly aligned with respect to each other, which requires a robust real-time tracking strategy-one of the bottlenecks of AR applications. In this paper, we describe the limitations and advantages of different optical tracking technologies, and we present our customized implementation of both recursive tracking and tracking by detection approaches. The second approach requires the implementation of a classifier and we propose the use of a Random Forest classifier. We evaluated both approaches in the context of an AR application for design review. Some conclusions regarding the performance of each approach are given.

show abstract

Section: Tracking By Detectionmentioning

confidence: 99%

Real-time optical markerless tracking for augmented reality applications

Barandiarán

Paloc

Graña

2009

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…Another idea is to consider interest-point matching as a classification problem. The features from the reference image are used to train the classifier [4], [19].…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Interest-Point-Matching Algorithm for High-Resolution Satellite Images

Xiong

Zhang

2009

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Interest-point matching is a key technique for image registration. It is widely used for 3-D shape reconstruction, change detection, medical image processing, computerized visioning systems, and pattern recognition. Although numerous algorithms have been developed for different applications, processing local distortion inherent in images that are captured from different viewpoints remains problematic. High-resolution satellite images are normally acquired at widely spaced intervals and typically contain local distortion due to ground relief variation. Interestpoint-matching algorithms can be grouped into two broad categories: area based and feature based. Although each type has its own particular advantages in specific applications, they all face the common problem of dealing with ambiguity in smooth (lowtexture) areas, such as grass, water, highway surfaces, building roofs, etc. In this paper, a new algorithm for interest-point matching of high-resolution satellite images is proposed. The conceptual basis of this algorithm is the detection of "super points," those points which have the greatest interest strength (i.e., which represent the most prominent features) and the subsequent construction of a control network. Sufficient spatial information is then available to reduce the ambiguity and avoid false matches. We commence this paper with a brief review of current research on interest-point matching. We then introduce the proposed algorithm in detail and describe experiments with three sets of high-resolution satellite images. The experiment results show that the proposed algorithm can successfully process local distortion in high-resolution satellite images and can avoid ambiguity in matching the smooth areas. It is simple, fast, and accurate.Index Terms-Control network, high-resolution satellite image, interest-point matching, super point.

show abstract

“…In the case of using RDTs for classification, the estimated pose can further be used to update the decision Trees to the actual viewing conditions at runtime (Boffy et al, 2006) . Our experiments showed that this can significantly improve the matching performance and makes it more robust to illumination changes, such as cast shadows or reflections.…”

Section: The Matching and Pose Estimation Phasementioning

confidence: 99%

Real-Time Object Detection and Tracking for Industrial Applications

Benhimane¹,

Najafi²,

Grundmann³

et al. 2008

Proceedings of the Third International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Real-time tracking of complex 3D objects has been shown to be a challenging task for industrial applications where robustness, accuracy and run-time performance are of critical importance. This paper presents a fully automated object tracking system which is capable of overcoming some of the problems faced in industrial environments. This is achieved by combining a real-time tracking system with a fast object detection system for automatic initialization and re-initialization at run-time. This ensures robustness of object detection, and at the same time accuracy and speed of recursive tracking. For the initialization we build a compact representation of the object of interest using statistical learning techniques during an off-line learning phase, in order to achieve speed and reliability at run-time by imposing geometric and photometric consistency constraints. The proposed tracking system is based on a novel template management algorithm which is incorporated into the ESM algorithm. Experimental results demonstrate the robustness and high precision of tracking of complex industrial machines with poor textures under severe illumination conditions.

show abstract

Real-Time Feature Matching using Adaptive and Spatially Distributed Classification Trees

Cited by 10 publications

References 15 publications

Real-time optical markerless tracking for augmented reality applications

Real-time optical markerless tracking for augmented reality applications

A Novel Interest-Point-Matching Algorithm for High-Resolution Satellite Images

Real-Time Object Detection and Tracking for Industrial Applications

Contact Info

Product

Resources

About