Active mobile vehicle bottom dangerous goods detection device based on deep learning algorithm

Abstract

The invention relates to an active mobile vehicle bottom dangerous goods detection device based on a deep learning algorithm. The system comprises an information acquisition device and an industrial personal computer. The information acquisition device is in wireless communication with the industrial personal computer. The information acquisition device comprises an industrial camera, a light supplementing lamp, a radiation sensor, a gas sensor and a wireless transmission module. The information acquisition device further comprises a mobile platform, the mobile platform comprises a motion controller, an infrared wireless module and a remote controller, and the mobile platform is controlled by the remote controller to traverse the vehicle bottom through a U-shaped route. The controller is connected with a remote controller through an infrared wireless module. An industrial camera is installed on the upper surface of a machine body of the mobile platform. Light supplementing lamps are symmetrically arranged on the machine body on the front side and the rear side of the industrial camera, and a deep learning algorithm is loaded in the industrial personal computer. The device is an active mobile detection device, that is, after parking, the mobile detection device is actively operated to enter the vehicle bottom for detection, dangerous target detection can be better achieved, andthe detection precision is high.

Description

technical field [0001] The invention relates to the field of robot target detection, in particular to an active mobile bottom dangerous goods detection device based on a deep learning algorithm. Background technique [0002] With the rapid development of the economy, the number of cars in my country has increased sharply. By the end of 2016, the number of civilian cars in my country has reached 180 million. Cars have become an indispensable means of transportation for our lives. However, due to the fact that dangerous goods are easily hidden at the bottom of the vehicle, it is highly concealed and difficult to check, which is likely to cause great harm to society. In recent years, countries all over the world have raised the research on under-vehicle security inspection technology and devices to the height of national development strategy due to various considerations such as international anti-terrorism and public safety. [0003] The current under-vehicle detection device...

AI Technical Summary

Problems solved by technology

The fixed type generally digs the camera and the supplementary light on the road and installs it. When the vehicle passes by, the camera is triggered to take pictures and scans; the principle of the mobile type is similar to the fixed type, that is, the camera and the supplementary light are integrated into a mobile On the device, place it in the middle of the road surface when security inspection is required, and when the vehicle passes above, trigger the camera to take pictures and scan, such as the applicant's prior application CN2018114156704 Vehicle chassis detection system and vehicle chassis detection method, the device adopts passive detection, that is The device is placed on the road when needed, and the vehicle passes through it to trigger the line-scan camera to take pictures and scan. However, the image obtained by using the line-scan camera is too large (generally up to 7000*2000), and the image used It is difficult to obtain training images for recognition technology, resulting in low recognition accuracy

[0004] The existing under-vehicle detection device can realize non-stop detection, and has the advantages of fast detection speed and simple detection method. However, for some occasions that require relatively high security inspection levels, such as the entrance of large international conference venues and military venues, its detection accuracy The requirement is higher than the detection speed. The existing technology generally uses the overall scanning technology of the bottom of the vehicle, and then uses manual detection, so that the detection speed is faster, and the detection time of a vehicle is about 5s. Detection is easy to cause fatigue and missed detection

However, if manual detection is replaced by traditional target detection technology, there are also problems such as low recognition accuracy, inaccurate positioning, and detection targets that cannot be classified.

Images