Human and Object Detection in Smoke-Filled Space Using Millimeter-Wave Radar Based Measurement

2006 ◽  
Vol 18 (6) ◽  
pp. 760-764 ◽  
Author(s):  
Yoshimitsu Aoki ◽  
◽  
Masaki Sakai
Keyword(s):  
Image Processing ◽  
Object Detection ◽  
Millimeter Wave ◽  
Important Task ◽  
3D Image ◽  
3D Image Processing ◽  
Millimeter Wave Radar ◽  
Wave Radar ◽  
Measurement Experiment ◽  
Do So

One of the greatest problems in rescue operations during fire disasters is the blocking of firefighters’ view by dense smoke. Assuming that a firefighter’s most important task is to understand the situation within a smoke-filled space. We developed a way to do so, starting by scanning space using millimeter-wave radar combined with a gyrosensor. To detect persons and objects, we constructed a 3D map from signal reflection datasets using 3D image processing. We detail our proposal and report results of measurement experiment in actual smoke-filled areas.

Radar and vision fusion for the real-time obstacle detection and identification

2019 ◽  
Vol 46 (3) ◽  
pp. 391-395 ◽  
Author(s):  
Xinyu Zhang ◽  
Mo Zhou ◽  
Peng Qiu ◽  
Yi Huang ◽  
Jun Li
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Real Time ◽  
Millimeter Wave ◽  
Obstacle Detection ◽  
Content Type ◽  
Millimeter Wave Radar ◽  
Bounding Box ◽  
Detection And Identification ◽  
Wave Radar

Purpose The purpose of this paper is the presentation and research of a novel sensor fusion-based system for obstacle detection and identification, which uses the millimeter-wave radar to detect the position and velocity of the obstacle. Afterwards, the image processing module uses the bounding box regression algorithm in deep learning to precisely locate and identify the obstacles. Design/methodology/approach Unlike the traditional algorithms that use radar and vision to detect obstacles separately, the purposed method of this paper uses radar to determine the approximate location of obstacles and then uses bounding box regression to achieve accurate positioning and recognition. First, the information of the obstacles can be acquired by the millimeter-wave radar, and the effective target is extracted by filtering the data. Then, use coordinate system conversion and camera parameter calibration to project the effective target to the image plane, and generate the region of interest (ROI). Finally, based on image processing and machine learning techniques, the vehicle targets in the ROI are detected and tracked. Findings The millimeter wave is used to determine the presence of an obstacle, and the deep learning algorithm of the image is combined to determine the shape and the class of the obstacle. The experimental results indicate that the detection rate of this method is up to 91.6 per cent, which can better implement the perception of the environment in front of the vehicle. Originality/value The originality is based on the combination of millimeter-wave sensors and deep learning. Using the bounding box regression algorithm in RCNN, the ROI detected by radar is analyzed to realize real-time obstacle detection and recognition. This method does not require processing the entire image, greatly reducing the amount of data processing and improving the efficiency of the algorithm.

The Large Millimeter Wave Radar Phased Antenna Array

2000 ◽  
Vol 54 (10) ◽  
pp. 101-111
Author(s):  
Aleksey Alekseevich Tolkachev ◽  
Vasiliy Andreevich Makota ◽  
Mariya Petrovna Pavlova ◽  
Anatoliy Moiseevich Nikolaev ◽  
Vladimir Victorovich Denisenko ◽  
...  
Keyword(s):  
Antenna Array ◽  
Millimeter Wave ◽  
Millimeter Wave Radar ◽  
Wave Radar ◽  
Phased Antenna Array

Antenna for Navigational Shipborne Millimeter-Wave Radar

2006 ◽  
Vol 65 (16) ◽  
pp. 1453-1462
Author(s):  
A. N. Nechiporenko ◽  
L. D. Fesenko
Keyword(s):  
Millimeter Wave ◽  
Millimeter Wave Radar ◽  
Wave Radar
Sign in / Sign up

Export Citation Format

Share Document