Street litter recognition method applied in complex environment

Abstract

The invention relates to a street litter recognition method. The street litter recognition method applied in a complex environment comprises the following steps that 1, a street picture is acquired, litter areas and litter-free areas are chopped, and a sample set is constructed for training a deep convolutional neural network (DCNN); 2, registration and pixel level differentiation are conducted on a to-be-detected real-time street picture and a clean street picture to obtain changed areas of the image, whether the areas are litter or not is judged according to the output vector of the deep convolutional neural network (DCNN), and if yes, marks are made on the real-time image. According to the method, detection errors caused by interference factors such as the complex environment and illumination changes can be effectively inhibited while the litter targets are not missed, and all-weather street litter recognition in the complex environment is achieved.

Description

technical field [0001] The invention belongs to the field of computer vision and machine learning, and in particular relates to a street garbage identification method. Background technique [0002] With the rapid development of social and economic level, the living standard of residents has improved significantly, the consumption of goods has increased rapidly, and the discharge of garbage has also increased, which not only pollutes the environment, but also affects the appearance of the city. [0003] At present, the main way to deal with street garbage is regular inspection and cleaning by sanitation workers. Since the generation of garbage has no fixed time and space rules, this method is likely to cause untimely cleaning or no garbage is found after inspection, thus wasting manpower , and cannot guarantee urban sanitation and image. Therefore, it is extremely urgent and valuable to adopt a method that can remotely monitor the street garbage situation in real time and re...

AI Technical Summary

Problems solved by technology

This method realizes all-weather monitoring and detection of urban disorderly garbage, but this method is to detect the entire image. Since the error rate of the deep learning network is always impossible to be 0, the more non-garbage objects are detected, the more false detections will occur. The greater the probability, and the urban scene is extremely complex, often there will be static objects similar to garbage but not garbage appearing in the background, which will undoubtedly bring a lot of false detections to this method

Images