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

Abstract

The present invention is an active mobile bottom dangerous goods detection device based on a deep learning algorithm, including information collection equipment and an industrial computer, and the information collection equipment and the industrial computer communicate through wireless communication, wherein the information collection equipment includes an industrial camera, a supplementary light, and a radiation sensor , a gas sensor, and a wireless transmission module, the information collection device also includes a mobile platform, the mobile platform includes a motion controller, an infrared wireless module, and a remote controller, and the remote controller controls the mobile platform to traverse the bottom of the vehicle through a 'U-shaped' route ;The controller is connected to the remote control through an infrared wireless module; an industrial camera is installed on the upper surface of the mobile platform, and the front and rear sides of the industrial camera are symmetrically arranged with fill lights, and the industrial computer is loaded with a deep learning algorithm . The device is an active mobile detection device, that is, after parking, the mobile detection device is actively operated to enter the bottom of the vehicle for detection, which can better realize the detection of dangerous targets and has high detection accuracy.

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