Article detection network method based on camera projection model

Abstract

The invention discloses an article detection network method based on a camera projection model, and the method comprises the steps: inputting an image, and designing and calculating an anchor frame ofthe input image; adopting a backbone network: inputting the image into the backbone network, and outputting the image after passing through a plurality of feature layers; designing Razor modules; encoding Ground truth, and then predicting; screening negative samples; training the selection sample, designing a loss function, and performing training to obtain a training model; applying a model: after the training is finished, carrying out model derivation by using the obtained function parameters, estimating each obtained anchor frame to obtain the probability that a target exists under the anchor frame, and carrying out back-stepping to obtain the real position in the actual image. According to the article detection network method provided by the invention, the calculation amount is greatly reduced, and meanwhile, the accurate detection performance of the network is still kept. In the two industries of automatic driving and monitoring which are very dependent on a camera projection model, the high-efficiency characteristic of the method is proved, and a very good effect is achieved.

Description

technical field [0001] The present invention relates to the field of network object detection, and more specifically, to an object detection network method and system based on a camera projection model. Background technique [0002] Convolutional neural network (CNN), as a very popular carrier for image recognition and detection, has achieved great success. Based on this technology, many application networks have been derived, such as VGG, ResNet, DenseNet, Yolo and other OneStage networks. . However, these end-to-end (End to End) networks for recognition have many practical problems: First, these networks require a huge amount of computation, making it impossible to actually implement them. The inability to implement includes two levels. One is that the huge amount of calculation leads to higher GPU usage, which increases the deployment cost. The second level is that the huge amount of calculation makes it difficult to achieve real-time calculation. In order to achieve rea...

AI Technical Summary

Problems solved by technology

However, these end-to-end (End to End) networks for recognition have many practical problems: First, these networks require a huge amount of calculations, making it impossible to actually land

The inability to implement includes two levels. One is that the huge amount of calculation leads to higher GPU usage, which increases the deployment cost. The second level is that the huge amount of calculation makes it difficult to achieve real-time calculation. In order to achieve real-time calculation, often need Deploying more computing equipment will cause waste of resources while increasing costs

Second, directly using the simplified network models of these classic networks cannot achieve the performance of the network very well.

Third, some networks with good performance do not design the network for the projection model of the camera, but prefer the network design based on the image itself. This design is more general, but not efficient.

Images