An Enhanced Histogram of Oriented Gradients for Pedestrian Detection

Zhao, Yong; Zhang, Yongjun; Cheng, Ruzhong; Wei, Daimeng; Li, Guoliang

doi:10.1109/mits.2015.2427366

Cited by 32 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in previous researches by Cao et al [ 14 ] and Nguyen et al [ 16 ], the HOG feature has been used for gender recognition. Originally, the HOG feature was successfully used for pedestrian detection [ 18 , 19 , 20 ]. Later, this feature extraction method was also successfully used for gender recognition [ 14 , 16 ], age estimation [ 21 ], and face recognition [ 22 , 23 ].…”

Section: Proposed Methodsmentioning

confidence: 99%

Enhanced Gender Recognition System Using an Improved Histogram of Oriented Gradient (HOG) Feature from Quality Assessment of Visible Light and Thermal Images of the Human Body

Nguyen

Park

2016

Sensors

View full text Add to dashboard Cite

With higher demand from users, surveillance systems are currently being designed to provide more information about the observed scene, such as the appearance of objects, types of objects, and other information extracted from detected objects. Although the recognition of gender of an observed human can be easily performed using human perception, it remains a difficult task when using computer vision system images. In this paper, we propose a new human gender recognition method that can be applied to surveillance systems based on quality assessment of human areas in visible light and thermal camera images. Our research is novel in the following two ways: First, we utilize the combination of visible light and thermal images of the human body for a recognition task based on quality assessment. We propose a quality measurement method to assess the quality of image regions so as to remove the effects of background regions in the recognition system. Second, by combining the features extracted using the histogram of oriented gradient (HOG) method and the measured qualities of image regions, we form a new image features, called the weighted HOG (wHOG), which is used for efficient gender recognition. Experimental results show that our method produces more accurate estimation results than the state-of-the-art recognition method that uses human body images.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Enhanced Gender Recognition System Using an Improved Histogram of Oriented Gradient (HOG) Feature from Quality Assessment of Visible Light and Thermal Images of the Human Body

Nguyen

Park

2016

Sensors

View full text Add to dashboard Cite

show abstract

“…In our proposed study color, texture or shape based evaluation made. There three types of images were taken (commercial images, medical images, group images) for identifying the strength of the retrieval system [8][9][10][11][12][13]. Totally 1500 images, from each type 500 images were maintained in the database, which are all environment independent collections.…”

Section: Simulation Resultsmentioning

confidence: 99%

Multi Object and Dynamic Query Based CBIR System using DCT Incorporated with HOG and HTF

2019

IJITEE

View full text Add to dashboard Cite

This work contributes multi object detection and dynamic query image based retrieval system. Generally, finding relevance and matching user expectations is very critical based on query key information and these results irrelevant responses which will produce low similarity index. Consequently, CBIR system took a major responsibility of identifying new objects, retrieving similar objects or contents based on multi query and dynamic keywords with improved recall and precision as per requirement of the users. At this juncture, Discrete Curvelet Transform with the incorporation of HOG and HTF based approach is proposed to handle commercial image, medical images and types of multi model images. This proposed approach mainly focuses on extracting scaled features for finding correlation among the query and database images. To start with the process, query image is decomposed into multi level sub images to extract set of texture features at two levels. These features are estimated by Gray Level Co-occurrence Matrix (GLCM) and HOG descriptor based techniques is adapted to find scaled vectors with reduced dimensionality. This method outperform compared as compared to existing method is authenticated from experimental results.

show abstract

“…The histogram from each block is then normalised, and all histograms are then combined to give a final feature vector corresponding to the image as a whole. This kind of feature vector has been used for a variety of image analysis problems [8,27].…”

Section: Introductionmentioning

confidence: 99%

Genetic Programming for Region Detection, Feature Extraction, Feature Construction and Classification in Image Data

Lensen

Al-Sahaf

Zhang

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Image analysis is a key area in the computer vision domain that has many applications. Genetic Programming (GP) has been successfully applied to this area extensively, with promising results. Highlevel features extracted from methods such as Speeded Up Robust Features (SURF) and Histogram of Oriented Gradients (HoG) are commonly used for object detection with machine learning techniques. However, GP techniques are not often used with these methods, despite being applied extensively to image analysis problems. Combining the training process of GP with the powerful features extracted by SURF or HoG has the potential to improve the performance by generating high-level, domaintailored features. This paper proposes a new GP method that automatically detects different regions of an image, extracts HoG features from those regions, and simultaneously evolves a classifier for image classification. By extending an existing GP region selection approach to incorporate the HoG algorithm, we present a novel way of using high-level features with GP for image classification. The ability of GP to explore a large search space in an efficient manner allows all stages of the new method to be optimised simultaneously, unlike in existing approaches. The new approach is applied across a range of datasets, with promising results when compared to a variety of well-known machine learning techniques. Some high-performing GP individuals are analysed to give insight into how GP can effectively be used with high-level features for image classification.

show abstract

An Enhanced Histogram of Oriented Gradients for Pedestrian Detection

Cited by 32 publications

References 21 publications

Enhanced Gender Recognition System Using an Improved Histogram of Oriented Gradient (HOG) Feature from Quality Assessment of Visible Light and Thermal Images of the Human Body

Enhanced Gender Recognition System Using an Improved Histogram of Oriented Gradient (HOG) Feature from Quality Assessment of Visible Light and Thermal Images of the Human Body

Multi Object and Dynamic Query Based CBIR System using DCT Incorporated with HOG and HTF

Genetic Programming for Region Detection, Feature Extraction, Feature Construction and Classification in Image Data

Contact Info

Product

Resources

About