From Local Features to Global Shape Constraints: Heterogeneous Matching Scheme for Recognizing Objects under Serious Background Clutter

2011 ◽  
pp. 64-75 ◽  
Author(s):  
Martin Klinkigt ◽  
Koichi Kise
Keyword(s):  
Local Features ◽  
Global Shape ◽  
Shape Constraints ◽  
Background Clutter

scholarly journals Parts Semantic Segmentation Aware Representation Learning for Person Re-Identification

2019 ◽  
Vol 9 (6) ◽  
pp. 1239 ◽  
Author(s):  
Hua Gao ◽  
Shengyong Chen ◽  
Zhaosheng Zhang
Keyword(s):  
Semantic Segmentation ◽  
Representation Learning ◽  
Local Features ◽  
Point Of View ◽  
Body Parts ◽  
Feature Maps ◽  
Benchmark Datasets ◽  
Background Clutter ◽  
Three Body ◽  
Global And Local

Person re-identification is a typical computer vision problem which aims at matching pedestrians across disjoint camera views. It is challenging due to the misalignment of body parts caused by pose variations, background clutter, detection errors, camera point of view variation, different accessories and occlusion. In this paper, we propose a person re-identification network which fuses global and local features, to deal with part misalignment problem. The network is a four-branch convolutional neural network (CNN) which learns global person appearance and local features of three human body parts respectively. Local patches, including the head, torso and lower body, are segmented by using a U_Net semantic segmentation CNN architecture. All four feature maps are then concatenated and fused to represent a person image. We propose a DropParts method to solve the parts missing problem, with which the local features are weighed according to the number of parts found by semantic segmentation. Since three body parts are well aligned, the approach significantly improves person re-identification. Experiments on the standard benchmark datasets, such as Market1501, CUHK03 and DukeMTMC-reID datasets, show the effectiveness of our proposed pipeline.

scholarly journals Integration of local features into a global shape

2001 ◽  
Vol 41 (14) ◽  
pp. 1785-1790 ◽  
Author(s):  
Jukka Saarinen ◽  
Dennis M Levi
Keyword(s):  
Local Features ◽  
Global Shape

scholarly journals Interpreting local visual features as a global shape requires awareness

2010 ◽  
Vol 278 (1715) ◽  
pp. 2207-2215 ◽  
Author(s):  
D. Samuel Schwarzkopf ◽  
Geraint Rees
Keyword(s):  
Discrimination Task ◽  
Response Times ◽  
Local Features ◽  
Orientation Discrimination ◽  
Visual Features ◽  
Shape Discrimination ◽  
Global Shape ◽  
Orientation Cues ◽  
Conscious Processing ◽  
The Brain

How the brain constructs a coherent representation of the environment from noisy visual input remains poorly understood. Here, we explored whether awareness of the stimulus plays a role in the integration of local features into a representation of global shape. Participants were primed with a shape defined either by position or orientation cues, and performed a shape-discrimination task on a subsequently presented probe shape. Crucially, the probe could either be defined by the same or different cues as the prime, which allowed us to distinguish the effect of priming by local features and global shape. We found a robust priming benefit for visible primes, with response times being faster when the probe and prime were the same shape, regardless of the defining cue. However, rendering the prime invisible uncovered a dissociation: position-defined primes produced behavioural benefit only for probes of the same cue type. Surprisingly, orientation-defined primes afforded an enhancement only for probes of the opposite cue. In further experiments, we showed that the effect of priming was confined to retinotopic coordinates and that there was no priming effect by invisible orientation cues in an orientation-discrimination task. This explains the absence of priming by the same cue in our shape-discrimination task. In summary, our findings show that while in the absence of awareness orientation signals can recruit retinotopic circuits (e.g. intrinsic lateral connections), conscious processing is necessary to interpret local features as global shape.

Fusion of Global Shape and Local Features Using Boosting for Object Class Recognition

2012 ◽  
pp. 444-448
Author(s):  
Noridayu Manshor ◽  
Amir Rizaan Abdul Rahiman ◽  
Mandava Rajeswari ◽  
Dhanesh Ramachandram
Keyword(s):  
Local Features ◽  
Object Class ◽  
Global Shape ◽  
Object Class Recognition

Recognition of Birds in Blurred and Illumination Images by Local Features

2017 ◽  
Vol 7 (7) ◽  
pp. 243
Author(s):  
Suresha .M ◽  
. Sandeep
Keyword(s):  
Computer Vision ◽  
Time Complexity ◽  
Feature Detection ◽  
Feature Matching ◽  
Fast Algorithms ◽  
Local Features ◽  
Experimental Demonstration ◽  
Harris Corner ◽  
Blurred Image ◽  
Blurred Images

Local features are of great importance in computer vision. It performs feature detection and feature matching are two important tasks. In this paper concentrates on the problem of recognition of birds using local features. Investigation summarizes the local features SURF, FAST and HARRIS against blurred and illumination images. FAST and Harris corner algorithm have given less accuracy for blurred images. The SURF algorithm gives best result for blurred image because its identify strongest local features and time complexity is less and experimental demonstration shows that SURF algorithm is robust for blurred images and the FAST algorithms is suitable for images with illumination.

Sign in / Sign up

Export Citation Format

Share Document