A video-based automatic detection method for falling objects from railway freight cars

Abstract

The invention belongs to the field of video processing and pattern recognition, and in particular relates to a video-based automatic detection method for railway wagon spills, which is based on background modeling-based moving target detection and neural network-based target recognition algorithms. Its background modeling-based moving target detection and neural network-based target recognition algorithm include the following steps: Step 1. Acquire video; Step 2. Establish the histogram gradient feature model of the train running part; Step 3. Use background modeling technology to extract Suspected spills; Step 4. Recognition of suspected spills based on neural network (ANN). The invention realizes the automatic detection and recognition of the spilled objects of the truck under the state of the train running at high speed, has high detection accuracy and low misclassification rate, and the fast detection speed also satisfies the actual engineering needs.

Description

technical field [0001] The invention belongs to the field of video processing and pattern recognition, and in particular relates to a video-based automatic detection method for railway wagon spills, which is based on background modeling-based moving target detection and neural network-based target recognition algorithms. Background technique [0002] During the operation of trains, especially freight cars and ordinary passenger cars, it is required to seal the compartments. When the train is running in a dynamic state, if the loaded goods are spilled, it will corrode the rails and pollute the environment, and at the worst, it will damage the stability of the running part, causing problems such as brakes and brake failure, which will lead to major safety accidents. At this stage, the detection and recognition of whether there are objects spilled in the compartment can only be carried out by human eyes, so not only the workload is heavy, but also it is difficult to observe whe...

AI Technical Summary

Problems solved by technology

In the dynamic state of the train running, if the loaded goods are spilled, it will corrode the rails and pollute the environment, and at the worst, it will damage the stability of the running part, causing problems such as brakes and brake failure, which will lead to major safety accidents

At this stage, the detection and recognition of whether there are objects spilled in the compartment can only be carried out by human eyes, so not only the workload is heavy, but also it is difficult to observe when the vehicle is far away from people, and when the distance is close and the speed is fast, the human eyes The resolution ability is poor, which makes it easy to miss detection

Images