Open Access
Distinctive Image Features from Scale-Invariant Keypoints
TLDR
The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.Abstract:
The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.read more
Citations
More filters
Proceedings ArticleDOI
Expanded Parts Model for Human Attribute and Action Recognition in Still Images
TL;DR: The proposed model relies on a collection of part templates which are learnt discriminatively to explain specific scale-space locations in the images (in human centric coordinates) and avoids the limitations of highly structured models.
Book ChapterDOI
Balancing deformability and discriminability for shape matching
TL;DR: This work presents the aspect shape context, which extends shape context-based descriptors and adaptively selects the "best" aspect weight for shape comparison, and shows that this framework naturally unifies existing important shape and image representations by adjusting the aspect weight and the embedding.
Proceedings ArticleDOI
Joint 2D-3D temporally consistent semantic segmentation of street scenes
Georgios Floros,Bastian Leibe +1 more
TL;DR: A novel Conditional Random Field formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecutive video frames and take advantage of the 3D scene geometry to improve segmentation quality is proposed.
Proceedings Article
Max-Margin Multiple-Instance Dictionary Learning
TL;DR: This paper designs a formulation to simultaneously learn mixtures of codes by maximizing classification margins in MIL, and results are observed in image classification benchmarks based on the learned codebooks, which observe both compactness and effectiveness.
Journal ArticleDOI
On-Road Pedestrian Tracking Across Multiple Driving Recorders
Kuan-Hui Lee,Jenq-Neng Hwang +1 more
TL;DR: A new framework to track on-road pedestrians across multiple driving recorders built upon the results of tracking under a single driving recorder to determine whether a specific pedestrian belongs to one or several cameras' field of views by considering association likelihood of the tracked pedestrians.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Proceedings ArticleDOI
A Combined Corner and Edge Detector
Chris Harris,Mike Stephens +1 more
TL;DR: The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
Journal ArticleDOI
A performance evaluation of local descriptors
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Journal ArticleDOI
Robust wide-baseline stereo from maximally stable extremal regions
TL;DR: The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.