Pedestrian Detection Based on Histograms of Oriented Gradients in ROI

2012 ◽  
Vol 542-543 ◽  
pp. 937-940
Author(s):  
Ping Shu Ge ◽  
Guo Kai Xu ◽  
Xiu Chun Zhao ◽  
Peng Song ◽  
Lie Guo
Keyword(s):  
Traditional Method ◽  
Detection Method ◽  
Feature Vector ◽  
Pedestrian Detection ◽  
Region Of Interest ◽  
Experimental Results ◽  
Process Time ◽  
Vertical Edge ◽  
Histograms Of Oriented Gradients

To locate pedestrian faster and more accurately, a pedestrian detection method based on histograms of oriented gradients (HOG) in region of interest (ROI) is introduced. The features are extracted in the ROI where the pedestrian's legs may exist, which is helpful to decrease the dimension of feature vector and simplify the calculation. Then the vertical edge symmetry of pedestrian's legs is fused to confirm the detection. Experimental results indicate that this method can achieve an ideal accuracy with lower process time compared to traditional method.

scholarly journals Random Forest with Adaptive Local Template for Pedestrian Detection

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Tao Xiang ◽  
Tao Li ◽  
Mao Ye ◽  
Zijian Liu
Keyword(s):  
Computer Vision ◽  
Random Forest ◽  
Classification Accuracy ◽  
Template Matching ◽  
Detection Method ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Sliding Window ◽  
Experimental Results ◽  
Training Samples

Pedestrian detection with large intraclass variations is still a challenging task in computer vision. In this paper, we propose a novel pedestrian detection method based on Random Forest. Firstly, we generate a few local templates with different sizes and different locations in positive exemplars. Then, the Random Forest is built whose splitting functions are optimized by maximizing class purity of matching the local templates to the training samples, respectively. To improve the classification accuracy, we adopt a boosting-like algorithm to update the weights of the training samples in a layer-wise fashion. During detection, the trained Random Forest will vote the category when a sliding window is input. Our contributions are the splitting functions based on local template matching with adaptive size and location and iteratively weight updating method. We evaluate the proposed method on 2 well-known challenging datasets: TUD pedestrians and INRIA pedestrians. The experimental results demonstrate that our method achieves state-of-the-art or competitive performance.

A Novel Fast Pedestrian Detection Method

2015 ◽  
Vol 738-739 ◽  
pp. 538-541
Author(s):  
Fu Qiang Zhou ◽  
Yan Li
Keyword(s):  
Video Streaming ◽  
Local Binary Pattern ◽  
Detection Method ◽  
Pedestrian Detection ◽  
Original Method ◽  
Histograms Of Oriented Gradients ◽  
Detection Approach

This paper presents novel pedestrian detection approach in video streaming, which could process frames rapidly. The method is based on cascades of HOG-LBP (Histograms of Oriented Gradients-Local Binary Pattern), but combines non-negative factorization to reduce the length of the feature, aiming at realizing a more efficient way of detection, remedying the slowness of the original method. Experiments show our method can process faster than HOG and HOG-LBP, and more accurate than HOG, which has better performance in pedestrian detection in video streaming.

PEDESTRIAN DETECTION SYSTEM USING CASCADED BOOSTING WITH INVARIANCE OF ORIENTED GRADIENTS

2009 ◽  
Vol 23 (04) ◽  
pp. 801-823 ◽  
Author(s):  
CHI-CHEN RAXLE WANG ◽  
JIN-YI WU ◽  
JENN-JIER JAMES LIEN
Keyword(s):  
Learning Algorithm ◽  
Detection System ◽  
Pedestrian Detection ◽  
Linear Interpolation ◽  
Detection Performance ◽  
Experimental Results ◽  
Computational Time ◽  
Aspect Ratios ◽  
Histograms Of Oriented Gradients ◽  
Interpolation Technique

This study presents a novel learning-based pedestrian detection system capable of automatically detecting individuals of different sizes and orientations against a wide variety of backgrounds, including crowds, even when the individual is partially occluded. To render the detection performance robust toward the effects of geometric and rotational variations in the original image, the feature extraction process is performed using both rectangular- and circular-type blocks of various sizes and aspect ratios. The extracted blocks are rotated in accordance with their dominant orientation(s) such that all the blocks extracted from the input images are rotationally invariant. The pixels within the cells in each block are then voted into rectangular- and circular-type 9-bin histograms of oriented gradients (HOGs) in accordance with their gradient magnitudes and corresponding multivariate Gaussian-weighted windows. Finally, four cell-based histograms are concatenated using a tri-linear interpolation technique to form one 36-dimensional normalized HOG feature vector for each block. The experimental results show that the use of the Gaussian-weighted window approach and tri-linear interpolation technique in constructing the HOG feature vectors improves the detection performance from 91% to 94.5%. In the proposed scheme, the detection process is performed using a cascaded detector structure in which the weak classifiers and corresponding weights of each stage are established using the AdaBoost self-learning algorithm. The experimental results reveal that the cascaded structure not only provides a better detection performance than many of the schemes presented in the literature, but also achieves a significant reduction in the computational time required to classify each input image.

scholarly journals A Fast Positioning Technology for Compensation Hole of Automobile Brake Master Cylinder

2021 ◽  
Vol 252 ◽  
pp. 01018
Author(s):  
Changfu Zhao ◽  
Hongchang Ding ◽  
Guohua Cao ◽  
Han Hou
Keyword(s):  
Traditional Method ◽  
Detection Method ◽  
The Self ◽  
Fine Tuning ◽  
Process Time ◽  
Detection Accuracy ◽  
Positioning Accuracy ◽  
Master Cylinder ◽  
Structural Part ◽  
Detection Speed

The compensation hole of the automobile brake master cylinder is an important structural part for adjusting the reservoir and pressure chamber of the brake master cylinder. Its detection accuracy is strictly controlled. However, because the compensation hole is located on the inner wall of the blind hole, the existing detection method cannot meet the testing needs. Therefore, this paper introduces the SSD model into the detection of the compensation hole of the brake master cylinder, and realizes the rapid positioning of the compensation hole by means of network fine-tuning. The compensation hole positioning detection is carried out on the self-developed automobile brake master cylinder compensation hole detector. The entire detection process time is about 5s, and the positioning accuracy is high. We apply the fine-tuning SSD model to the detection of the compensation hole of automobile brake master cylinder, which replaces the traditional method based on human-computer interaction to determine the position of the compensation hole. It has better detection accuracy and faster detection speed, and lays the foundation for the subsequent detection of the size of the compensation hole.

Research on Ultra-Weak Bioluminescence Detection and Features for Freshness of Corn

2015 ◽  
Vol 727-728 ◽  
pp. 239-243
Author(s):  
Hong Sheng Hu ◽  
Qun Feng Niu ◽  
Bo Yuan Cui
Keyword(s):  
Virtual Instrument ◽  
Traditional Method ◽  
Detection Method ◽  
Experimental Results ◽  
Nondestructive Examination ◽  
Safe Storage ◽  
Analysis System ◽  
Evident Relationship ◽  
Voltage Peak

Detection of ultra-weak bioluminescence for freshness of corn is not only a problem of corn safe storage but also related to corn quality. The paper built a Virtual Instrument platform based on LabVIEW and PXI4220 modularized hardware of NI. Then, a testing and analysis system for corn ultra-weak bioluminescence features was designed. Different freshness corns were tested and analyzed about the relation of freshness and ultra-weak bioluminescence features. The experimental results shows that the ultra-weak bioluminescence voltage peak values of different freshness corns all maximize about 1 hour, and voltage peak values between different freshness corns have no evident relationship. However, the ultra-weak bioluminescence voltage energy sum of different freshness corns increase progressively with the freshness degree. So, detection of voltage energy sum of different freshness corns can reflect wheat freshness effectively. Comparing with traditional method, the freshness detection method based on wheat ultra-weak bioluminescence features can realize precise, rapid and nondestructive examination.

scholarly journals Research on Pedestrian’s Detection Based on the Integration of AdaBoost Algorithm and Shape Features

2011 ◽  
Vol 2-3 ◽  
pp. 433-438
Author(s):  
Ying Yang ◽  
Yu Gang Ma ◽  
Xiao Dong Guo ◽  
Kun Jiao
Keyword(s):  
Detection Method ◽  
Pedestrian Detection ◽  
Morphological Characteristics ◽  
Vertical Axis ◽  
Adaptive Threshold ◽  
Candidate Region ◽  
Vertical Edge ◽  
Shape Features ◽  
Adaboost Algorithm ◽  
Axis Of Symmetry

In this Paper, Propose a Pedestrian Detection Method that Based on Adaboost Algorithm and Pedestrian Shape Features Integration. First According to the Collected Pedestrian True, False Sample, Selected the Characteristics of the Extended Class Haar, Adopt Adaboost Algorithm Training Get Pedestrian Classifier to Split the Initial Candidate Region of All Pedestrians in the Image. in this Paper, Propose an Adaptive Threshold Weight Update Method, Significantly Reduced the Number of the Characteristics of Strong Classifier, Optimize the Classifier Structure, Reduce the Complexity of the Algorithm; Meanwhile, the Online Update Detector, Improving the Reliability of the Detector. Pedestrian Leg Have Strong Vertical Edge Symmetry Characteristic so that Extracted the Vertical Edge Detection in the Initial Candidate Region, According to the Symmetry Determine the Vertical Axis of Symmetry, Combined with the Morphological Characteristics of Pedestrians to Determine the Width and Height Characteristics of the Pedestrian, to Determine the Pedestrian Candidate Region, Finally, Put a Further Validation to the Pedestrian Candidate Region.

Personal Identification Using Finger-Knuckle-Print Based on Local Binary Pattern

2013 ◽  
Vol 441 ◽  
pp. 703-706 ◽  
Author(s):  
Peng Fei Yu ◽  
Hao Zhou ◽  
Hai Yan Li
Keyword(s):  
Local Binary Pattern ◽  
Feature Vector ◽  
Region Of Interest ◽  
Local Features ◽  
Personal Identification ◽  
Experimental Results ◽  
Considerable Progress ◽  
Similarity Measurement ◽  
Biometric Recognition ◽  
Histogram Intersection

Over the last ten years, considerable progress has been made on the new hand-based biometric recognition, such as palmprint and hand vein. During this period, it has been proved that Finger-Knuckle-Print (FKP) can be used as a biometric identifier. In this paper, we present an effective FKP identification method based on Local Binary Pattern (LBP), whose idea is to divide the region of interest (ROI) of FKP into a set of sub-image blocks, which can be applied to extract the local features of the FKP. After that, LBP histograms of image blocks in a FKP ROI image are connected together to build the feature vector of the FKP ROI image. In the match stage, histogram intersection distance is applied as the similarity measurement between sample and template. Experimental results conducted on a database of 165 persons (4 fingers per person) show that the proposed method is effective.

Study on Pedestrian Detection Method Based on HOG Features and SVM

2011 ◽  
Vol 268-270 ◽  
pp. 1786-1791
Author(s):  
Hai Yan Xi ◽  
Zhi Tao Xiao ◽  
Fang Zhang
Keyword(s):  
Detection Method ◽  
Detection System ◽  
Pedestrian Detection ◽  
Experimental Results ◽  
Input Vector ◽  
Vehicle Safety ◽  
Complex Background ◽  
Trained Classifier ◽  
Svm Algorithm

The research of pedestrian detection ahead of vehicle is the front direction in the field of vehicle safety assistant driving at present. The method of SVM pedestrian detection based on HOG features is studied in this paper. Firstly, the histograms of oriented gradient features between pedestrian and non-pedestrian samples are extracted. Then the features are used as an input vector of SVM algorithm, getting pedestrian classifier with a higher recognition by training. Finally the trained classifier is loaded into the online pedestrian detection system to detect the transport road image. The experimental results show that the algorithm can effectively identify the different scales and attitude pedestrian in complex background.

scholarly journals Cut-Edge Detection Method for Rice Harvesting Based on Machine Vision

Agronomy ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 590
Author(s):  
Zhenqian Zhang ◽  
Ruyue Cao ◽  
Cheng Peng ◽  
Renjie Liu ◽  
Yifan Sun ◽  
...  
Keyword(s):  
Machine Vision ◽  
Edge Detection ◽  
Detection Method ◽  
Region Of Interest ◽  
Average Error ◽  
Vertical Projection ◽  
Cut Edge ◽  
Fitting Method ◽  
Combine Harvester ◽  
Edge Detection Method

A cut-edge detection method based on machine vision was developed for obtaining the navigation path of a combine harvester. First, the Cr component in the YCbCr color model was selected as the grayscale feature factor. Then, by detecting the end of the crop row, judging the target demarcation and getting the feature points, the region of interest (ROI) was automatically gained. Subsequently, the vertical projection was applied to reduce the noise. All the points in the ROI were calculated, and a dividing point was found in each row. The hierarchical clustering method was used to extract the outliers. At last, the polynomial fitting method was used to acquire the straight or curved cut-edge. The results gained from the samples showed that the average error for locating the cut-edge was 2.84 cm. The method was capable of providing support for the automatic navigation of a combine harvester.

Sign in / Sign up

Export Citation Format

Share Document