Zobrazeno 1 - 10
of 178
pro vyhledávání: '"Chan, Kap Luk"'
In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain discrimin
Externí odkaz:
http://arxiv.org/abs/1605.04502
Publikováno v:
IEEE Transactions on Image Processing, vol. 24, no. 4, April 2015
In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer
Externí odkaz:
http://arxiv.org/abs/1511.07940
In this paper, we present a novel method based on online target-specific metric learning and coherent dynamics estimation for tracklet (track fragment) association by network flow optimization in long-term multi-person tracking. Our proposed framewor
Externí odkaz:
http://arxiv.org/abs/1511.06654
Autor:
Wang, Junyan, Chan, Kap-Luk
The same type of objects in different images may vary in their shapes because of rigid and non-rigid shape deformations, occluding foreground as well as cluttered background. The problem concerned in this work is the shape extraction in such challeng
Externí odkaz:
http://arxiv.org/abs/1412.8287
Autor:
Wang, Junyan, Chan, Kap Luk
In object segmentation by active contours, the initial contour is often required. Conventionally, the initial contour is provided by the user. This paper extends the conventional active contour model by incorporating feature matching in the formulati
Externí odkaz:
http://arxiv.org/abs/1307.6303
Autor:
Wang, Junyan, Chan, Kap Luk
In this paper, we propose a unified energy minimization model for the segmentation of non-smooth image structures. The energy of piecewise linear patch reconstruction is considered as an objective measure of the quality of the segmentation of non-smo
Externí odkaz:
http://arxiv.org/abs/1207.5113
Autor:
Wang, Junyan, Chan, Kap Luk
Curve evolution is often used to solve computer vision problems. If the curve evolution fails to converge, we would not be able to solve the targeted problem in a lifetime. This paper studies the theoretical aspect of the convergence of a type of gen
Externí odkaz:
http://arxiv.org/abs/1206.4042
Autor:
Wang, Junyan, Chan, Kap Luk
Conventional edge-based active contours often require the normal component of an edge indicator function on the optimal contours to approximate zero, while the tangential component can still be significant. In real images, the full gradients of the e
Externí odkaz:
http://arxiv.org/abs/1204.6458
Publikováno v:
In Computer Vision and Image Understanding March 2015 132:39-55
