Vehicle appearance feature recognition method and device, vehicle retrieval method and device, storage medium and electronic equipment
An identification method and vehicle technology, which are applied in the fields of storage media and electronic equipment, devices, vehicle retrieval methods, and vehicle appearance feature identification methods, and can solve problems such as subtle changes in difficult vehicles.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] figure 1 is a flow chart of a method for recognizing vehicle appearance features according to Embodiment 1 of the present invention.
[0066] refer to figure 1 , in step S101, a plurality of region segmentation results of the target vehicle are obtained from the image to be recognized.
[0067]In this embodiment, in terms of the content contained in the image, the image to be recognized may be an image including a part of the target vehicle or an image including the entire target vehicle. In terms of image types, the image to be recognized may be a captured still image, or a video image in a video frame sequence, or may be a synthesized image or the like. The multiple region segmentation results respectively correspond to regions of different orientations of the target vehicle. Specifically, the plurality of region segmentation results include segmentation results of the front, rear, left, and right sides of the target vehicle. Certainly, in the embodiment of the pr...
Embodiment 2
[0075] figure 2 is a flow chart of a method for recognizing vehicle appearance features according to Embodiment 2 of the present invention.
[0076] refer to figure 2 , in step S201, a plurality of region segmentation results of the target vehicle are obtained from the image to be recognized through the first neural network for region extraction.
[0077] Wherein, the first neural network may be any appropriate neural network capable of region extraction or target object recognition, including but not limited to convolutional neural network, reinforcement learning neural network, generation network in adversarial neural network, and the like. The setting of the specific structure in the neural network can be appropriately set by those skilled in the art according to actual needs, such as the number of convolutional layers, the size of the convolution kernel, the number of channels, etc., which are not limited in the embodiment of the present invention. In the embodiment of...
Embodiment 3
[0103] Figure 7 It is a flow chart of the vehicle retrieval method according to the third embodiment of the present invention.
[0104] refer to Figure 7 , in step S301, the appearance characteristic data of the target vehicle in the image to be retrieved is obtained by the recognition method of the appearance characteristic of the vehicle.
[0105] In this embodiment, the appearance feature data of the target vehicle in the image to be retrieved can be acquired through the recognition method of the vehicle appearance feature provided in the first embodiment or the second embodiment above. Wherein, the appearance feature data may be data represented by a vector. In terms of content contained in the image, the image to be retrieved may be an image including a part of the target vehicle or an image including the entire target vehicle. In terms of image types, the image to be retrieved may be a captured still image, or a video image in a sequence of video frames, or may be a...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More