Stereo-based region of interest generation for real-time pedestrian detection

2013 ◽  
Vol 8 (2) ◽  
pp. 181-188 ◽  
Author(s):  
Joohee Kim ◽  
Maral Mesmakhosroshahi
Keyword(s):  
Real Time ◽  
Pedestrian Detection ◽  
Region Of Interest

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.

Augmented Reality Overlay System for Computer-guided Needle Procedures

1969 ◽  
Author(s):  
Zachary Baum
Keyword(s):  
Augmented Reality ◽  
Real Time ◽  
Region Of Interest ◽  
Calibration Method ◽  
Position Error ◽  
Ct Image ◽  
Entire System ◽  
Projected Image ◽  
Needle Interventions

Purpose: Augmented reality overlay systems can be used to project a CT image directly onto a patient during procedures. They have been actively trialed for computer-guided procedures, however they have not become commonplace in practice due to restrictions of previous systems. Previous systems have not been handheld, and have had complicated calibration procedures. We put forward a handheld tablet-based system for assisting with needle interventions. Methods: The system consists of a tablet display and a 3-D printed reusable and customizable frame. A simple and accurate calibration method was designed to align the patient to the projected image. The entire system is tracked via camera, with respect to the patient, and the projected image is updated in real time as the system is moved around the region of interest. Results: The resulting system allowed for 0.99mm mean position error in the plane of the image, and a mean position error of 0.61mm out of the plane of the image. This accuracy was thought to be clinically acceptable for tool using computer-guidance in several procedures that involve musculoskeletal needle placements. Conclusion: Our calibration method was developed and tested using the designed handheld system. Our results illustrate the potential for the use of augmented reality handheld systems in computer-guided needle procedures. 

scholarly journals Building Feature Pool Effectively for Real-Time Pedestrian Detection

2018 ◽  
Vol 1069 ◽  
pp. 012107
Author(s):  
Jijun Yang ◽  
Yingdong Ma ◽  
Zhibin Zhang
Keyword(s):  
Real Time ◽  
Pedestrian Detection

scholarly journals Real-Time Runway Detection for Infrared Aerial Image Using Synthetic Vision and an ROI Based Level Set Method

2018 ◽  
Vol 10 (10) ◽  
pp. 1544 ◽  
Author(s):  
Changjiang Liu ◽  
Irene Cheng ◽  
Anup Basu
Keyword(s):  
Real Time ◽  
Level Set Method ◽  
Level Set ◽  
Infrared Image ◽  
Region Of Interest ◽  
Aerial Image ◽  
Real Time Processing ◽  
Synthetic Vision ◽  
Level Set Function ◽  
Rough Region

We present a new method for real-time runway detection embedded in synthetic vision and an ROI (Region of Interest) based level set method. A virtual runway from synthetic vision provides a rough region of an infrared runway. A three-thresholding segmentation is proposed following Otsu’s binarization method to extract a runway subset from this region, which is used to construct an initial level set function. The virtual runway also gives a reference area of the actual runway in an infrared image, which helps us design a stopping criterion for the level set method. In order to meet the needs of real-time processing, the ROI based level set evolution framework is implemented in this paper. Experimental results show that the proposed algorithm is efficient and accurate.

scholarly journals Research on Lightweight Infrared Pedestrian Detection Model Algorithm for Embedded Platform

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Zhaoli Wu ◽  
Xin Wang ◽  
Chao Chen
Keyword(s):  
Real Time ◽  
Target Detection ◽  
Pedestrian Detection ◽  
Infrared Image ◽  
Far Infrared ◽  
Detection Algorithm ◽  
Model Parameters ◽  
Detection Accuracy ◽  
Detection Model ◽  
Embedded Platform

Due to the limitation of energy consumption and power consumption, the embedded platform cannot meet the real-time requirements of the far-infrared image pedestrian detection algorithm. To solve this problem, this paper proposes a new real-time infrared pedestrian detection algorithm (RepVGG-YOLOv4, Rep-YOLO), which uses RepVGG to reconstruct the YOLOv4 backbone network, reduces the amount of model parameters and calculations, and improves the speed of target detection; using space spatial pyramid pooling (SPP) obtains different receptive field information to improve the accuracy of model detection; using the channel pruning compression method reduces redundant parameters, model size, and computational complexity. The experimental results show that compared with the YOLOv4 target detection algorithm, the Rep-YOLO algorithm reduces the model volume by 90%, the floating-point calculation is reduced by 93.4%, the reasoning speed is increased by 4 times, and the model detection accuracy after compression reaches 93.25%.

Sign in / Sign up

Export Citation Format

Share Document