A Space-Based Multi-viewpoint Collaborative Track Surrounding Environment Detection Method
A surrounding environment and detection method technology, applied in the field of aerial surveillance, can solve problems such as limited viewing angles and limitations, and achieve the effects of expanding coverage, improving reliability, improving efficiency and accuracy
Active Publication Date: 2020-05-26
BEIHANG UNIV
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problem of limited viewing angles of space-based patrol inspection, the present invention proposes a space-based multi-viewpoint collaborative track surrounding environment detection method; using multi-unmanned aerial vehicles to coordinate and cooperate, the track surrounding environment is photographed from different angles, and the ground is different Objects in the position can be detected and processed by ensuring that they have a picture with a good viewing angle; greatly improving the reliability of taking pictures, effectively solving the problem of limited viewing angles during single-drone inspections, and improving the efficiency and accuracy of railway inspections
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] The present invention will be further described in detail with reference to the accompanying drawings and embodiments.
[0025] Due to the long extension distance of the railway line and the large coverage area, the traditional manual inspection method is inefficient. Space-based surveillance by drones from the sky can effectively expand the surveillance range and improve work efficiency. However, due to the problem of UAV load and power consumption, the single flight time is relatively short. At the same time, when the UAV is taking aerial photos, it is difficult to ensure that a single flight can capture a picture with an effective perspective for the target object. Therefore, the present invention proposes to use multiple unmanned aerial vehicles to fly different routes and shoot ground targets from different angles of view, so as to obtain pictures of different angles of view of the target object. On the basis of these rich image data, better inspection results ca...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a space-based multi-viewpoint coordinated track peripheral environment detection method, which belongs to the field of aviation surveillance. Firstly, the high-definition camera carried by each UAV shoots the periphery of the track from different angles, and all the videos are time-aligned to extract pictures frame by frame; each frame aligned by time is selected in turn, and the salient area with a good viewing angle is selected. Then, each feature map is learned separately through the convolutional neural network, and the corresponding feature maps with the salient regions extracted are obtained. Finally, the feature maps are fused to obtain the overall macro feature map of the global features. The neural network makes a total judgment on the fused overall macroscopic feature map to obtain the final detection and judgment result. Select the next time-aligned frame and repeat the above steps until all objects in the pictures are detected. The invention effectively expands the coverage of the unmanned aerial vehicle monitoring, improves the operating efficiency of the space-based monitoring, and improves the detection and recognition accuracy of key points.
Description
technical field [0001] The invention belongs to the field of aviation surveillance, and in particular relates to a space-based multi-viewpoint collaborative orbit surrounding environment detection method. Background technique [0002] China has a vast territory of 9.6 million square kilometers, which also puts forward higher requirements for my country's transportation construction and transportation capacity. In recent years, in order to further serve the national economic construction and people's life, my country has increased investment and construction in the field of transportation. Among the many kinds of transportation, railway transportation occupies an important position; it is economical, fast, and has strong carrying capacity, which is the most suitable mode of transportation for my country's current national conditions. As of the end of 2016, China's total operating mileage of railways reached 124,000 kilometers, ranking second in the world in terms of scale; a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/10
Inventor 曹先彬甄先通李岩胡宇韬
Owner BEIHANG UNIV