scholarly journals Cascaded Sequential Attention for Object Recognition with Informative Local Descriptors and Q-learning of Grouping Strategies

2006 ◽  
Author(s):  
L. Paletta ◽  
G. Fritz ◽  
C. Seifert
Keyword(s):  
Object Recognition ◽  
Local Descriptors ◽  
Q Learning ◽  
Grouping Strategies

scholarly journals Selecting Discriminative Binary Patterns for a Local Feature

2015 ◽  
Vol 15 (3) ◽  
pp. 104-113
Author(s):  
Yingying Li ◽  
Jieqing Tan ◽  
Jinqin Zhong
Keyword(s):  
Object Recognition ◽  
Image Matching ◽  
State Of The Art ◽  
Local Feature ◽  
High Dimensionality ◽  
Learning Method ◽  
Local Descriptor ◽  
Local Descriptors

Abstract The local descriptors based on a binary pattern feature have state-of-the-art distinctiveness. However, their high dimensionality resists them from matching faster and being used in a low-end device. In this paper we propose an efficient and feasible learning method to select discriminative binary patterns for constructing a compact local descriptor. In the selection, a searching tree with Branch&Bound is used instead of the exhaustive enumeration, in order to avoid tremendous computation in training. New local descriptors are constructed based on the selected patterns. The efficiency of selecting binary patterns has been confirmed by the evaluation of these new local descriptors’ performance in experiments of image matching and object recognition.

3D object recognition based on local descriptors

2015 ◽  
Author(s):  
Marek Jakab ◽  
Wanda Benesova ◽  
Marek Racev
Keyword(s):  
Object Recognition ◽  
3D Object Recognition ◽  
Local Descriptors ◽  
3D Object

scholarly journals Human-level moving object recognition from traffic video

2015 ◽  
Vol 12 (2) ◽  
pp. 787-799 ◽  
Author(s):  
Fei Zhu ◽  
Quan Liu ◽  
Shan Zhong ◽  
Yang Yang
Keyword(s):  
Object Recognition ◽  
Optimization Method ◽  
Moving Object ◽  
Object A ◽  
Q Learning ◽  
Compact Region ◽  
Small Window ◽  
Object Region ◽  
Traffic Video ◽  
Intelligent Planning

Video preserves valuable raw information. Understanding these data and then recognizing objects and tagging them are crucial to intelligent planning and decision making. Deep learning provides us an effective way to understand big data with a human-level. As traffic video is characterized by crowded scene and low definition, it will be non-effective to deal with the whole image once. An alternative way is to separate image and determine a small window for each moving object. A Q-learning based moving object recognition approach, which firstly finds out moving object region and then uses a Q-learning based optimization method to determine the most compact region that contain the moving object, is proposed. The algorithms enable to detect the most compact rectangle around the moving object at near real-time speed. After that, a deep neural network is used to semantic tag the recognized objects. The experiment results show the algorithms work effectively.

scholarly journals Keypoint-Less, Heuristic Application of Local 3D Descriptors

2017 ◽  
Vol 42 (3) ◽  
pp. 239-255
Author(s):  
Bogdan Harasymowicz-Boggio ◽  
Łukasz Chechliński
Keyword(s):  
Object Recognition ◽  
State Of The Art ◽  
Massively Parallel ◽  
Classification Methods ◽  
Single Object ◽  
Local Descriptors ◽  
Indoor Scenes ◽  
Full Power ◽  
3D Descriptors ◽  
Hierarchical Manner

AbstractOne of the most important topics in the research concerning 3D local descriptors is computational efficiency. The state-of-the-art approach addressing this matter consists in using keypoint detectors that effectively limit the number of points for which the descriptors are computed. However, the choice of keypoints is not trivial and might have negative implications, such as the omission of relevant areas. Instead, focusing on the task of single object detection, we propose a keypoint-less approach to attention focusing in which the full scene is processed in a hierarchical manner: weaker, less rejective and faster classification methods are used as heuristics for increasingly robust descriptors, which allows to use more demanding algorithms at the top level of the hierarchy. We have developed a massively-parallel, open source object recognition framework, which we use to explore the proposed method on demanding, realistic indoor scenes, applying the full power available in modern computers.

Sign in / Sign up

Export Citation Format

Share Document