Method and device for locating a target object
A technology of target object and positioning method, which is applied in the field of target object positioning method and device, can solve the problem of heavy camera calibration workload, etc., and achieve the effects of good tracking, precise positioning, and road safety guarantee
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] The embodiment of the present invention provides a target object positioning method, such as figure 1 shown, including:
[0027] Step S110: Obtain original road image data, where the original road image data includes the target object. In a specific embodiment, the original road image data is acquired by cameras installed on both sides of the road, and the camera that acquires the original road image data may be an unregistered camera. The image noise is filtered out by means of Mann filtering, particle filtering, etc., and then the abnormal points of the image are eliminated by means of smoothing filtering. The target objects can be pedestrians, vehicles, etc.
[0028] Step S120: Divide the original road image data into blocks, and input the divided images into the image registration model. In a specific embodiment, since the computing power of the image registration model is limited, the original road image data needs to be cut into blocks first, and then input to...
Embodiment 2
[0065] The embodiment of the present invention provides a target object positioning device, such as Image 6 shown, including:
[0066] The original road image data acquisition module 110 is configured to acquire original road image data, and the original road image data includes the target object. For a detailed description, see the description of step S110 in the above embodiment 1.
[0067] The original road image data preprocessing module 120 is used for dividing the original road image data into blocks, and inputting the divided images into the image registration model. For a detailed description, refer to the description of step S120 in Embodiment 1 above.
[0068] The deformation vector obtaining module 130 is configured to obtain the deformation vector of each segmented image according to the image registration model. For a detailed description, see the description of step S130 in Embodiment 1 above.
[0069] The registration image obtaining module 140 is configured t...
Embodiment 3
[0073] The embodiment of the present invention provides a mobile terminal device, such as Figure 7 As shown, the computer device may include a processor 71 and a memory 72, wherein the processor 71 and the memory 72 may be connected by a bus or in other ways, Figure 7 Take the connection through the bus as an example.
[0074] The processor 71 may be a central processing unit (Central Processing Unit, CPU). The processor 71 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or Other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above types of chips.
[0075] As a non-transitory computer-readable storage medium, the memory 72 can be used to store non-transitory software pro...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More