阅读说明：本技术 自适应运动向量检测系统 (Adaptive motion vector detection system ) 是由 田华 于 2020-11-20 设计创作，主要内容包括：本发明涉及一种自适应运动向量检测系统,包括：向量检测设备,用于基于当前使用帧数选择从当前时刻的采集图像帧对应的目标区域起到之前的数个采集时刻分别对应的数个目标区域共计当前使用帧数的多个目标区域以执行对当前时刻的采集图像帧对应的目标区域中各个运动目标的各个运动向量的检测；编码执行设备,与向量检测设备连接,用于基于检测到的各个运动目标的各个运动向量对当前时刻的采集图像帧对应的目标区域进行编码。本发明的自适应运动向量检测系统原理可靠、方便操控。由于在场地图像的清晰度和对象数量的智能化检测的基础上,自适应设定执行对场地图像中运动向量检测所需要的图像帧的数量,从而兼顾了编码运算量和编码可靠度。(The invention relates to a self-adaptive motion vector detection system, comprising: the vector detection device is used for selecting a plurality of target areas with the total current use frame number from the target area corresponding to the current acquisition image frame to a plurality of target areas respectively corresponding to a plurality of previous acquisition moments on the basis of the current use frame number so as to detect each motion vector of each motion target in the target area corresponding to the current acquisition image frame; and the coding execution device is connected with the vector detection device and is used for coding the target area corresponding to the collected image frame at the current moment based on each detected motion vector of each motion target. The self-adaptive motion vector detection system is reliable in principle and convenient to operate and control. On the basis of intelligent detection of the definition and the number of objects of the field image, the number of image frames required by executing motion vector detection in the field image is set in a self-adaptive mode, and therefore coding computation and coding reliability are considered.)

1. An adaptive motion vector detection system, the system comprising:

the vector detection device is connected with the frame number selection mechanism and is used for selecting a plurality of target areas with the total current use frame number from the target area corresponding to the current acquisition image frame to a plurality of target areas respectively corresponding to a plurality of previous acquisition moments on the basis of the current use frame number so as to detect each motion vector of each motion target in the target area corresponding to the current acquisition image frame;

the encoding execution equipment is connected with the vector detection equipment and is used for encoding a target area corresponding to the acquired image frame at the current moment based on each detected motion vector of each motion target so as to obtain encoded data to be transmitted;

the eagle eye acquisition mechanism is arranged on a tennis match field and used for carrying out ultra-clear image acquisition at uniform time intervals on the tennis match field so as to obtain a plurality of continuous acquired image frames;

the band-pass filtering equipment is connected with the eagle eye acquisition mechanism and is used for performing band-pass filtering processing on each received acquired image frame to obtain a field processing image;

the field identification device is connected with the band-pass filtering device and used for identifying a target area only comprising a tennis field from the field processing image based on the imaging characteristics of the tennis field;

the cutting processing equipment is connected with the field recognition equipment and is used for cutting a target area from the field processing image so as to obtain a plurality of continuous target areas corresponding to a plurality of continuous acquisition image frames respectively;

the definition analysis equipment is connected with the cutting processing equipment and is used for extracting the definition of a target area corresponding to the collected image frame at the current moment to be output as the current definition;

the quantity identification device is connected with the definition analysis device and is used for identifying the quantity of the objects existing in the target area corresponding to the collected image frame at the current moment so as to obtain the quantity of the current objects;

the frame number selection mechanism is respectively connected with the definition analysis equipment and the number identification equipment and is used for determining the corresponding current using frame number based on the current definition and the current object number;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the higher the current definition is, the less the corresponding current using frame number is determined;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the smaller the number of current objects, the smaller the number of determined corresponding current usage frames.

2. The adaptive motion vector detection system of claim 1, wherein:

the band-pass filtering device, the field recognition device, the cutting processing device, the definition analysis device, the number recognition device and the frame number selection mechanism are all arranged in a control room of a tennis match field.

3. The adaptive motion vector detection system of claim 2, wherein the system further comprises:

and the data temporary storage mechanism is respectively connected with the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

4. The adaptive motion vector detection system of claim 3, wherein:

the data temporary storage mechanism is used for storing temporary storage data of the band-pass filter equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism respectively.

5. The adaptive motion vector detection system of claim 4, wherein:

the data temporary storage mechanism is also used for storing configuration parameters of the band-pass filter equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism respectively.

6. The adaptive motion vector detection system of claim 5, wherein the system further comprises:

and the uninterrupted power supply is respectively connected with the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

7. The adaptive motion vector detection system of claim 6, wherein:

the uninterrupted power supply is used for respectively providing required power supply voltage for the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

8. The adaptive motion vector detection system of claim 7, wherein:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition to be output comprises the following steps: and extracting the definition of each image block in a target area corresponding to the acquired image frame at the current moment to be used as each reference definition.

9. The adaptive motion vector detection system of claim 8, wherein:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition output further comprises the following steps: and sequencing the reference definitions, and removing the highest value and the lowest value to obtain more than one definition to be processed.

10. The adaptive motion vector detection system of claim 9, wherein:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition output further comprises the following steps: performing mean value calculation on the more than one definition to be processed to obtain the current definition;

the method for identifying the number of the objects in the target area corresponding to the acquired image frame at the current moment to obtain the current number of the objects comprises the following steps: and removing a background area in a target area corresponding to the acquired image frame at the current moment, and outputting the number of the remaining foreground image blocks as the number of the current objects.

Technical Field

The invention relates to the field of image coding and decoding, in particular to a self-adaptive motion vector detection system.

Background

In inter-frame coding, the relative displacement between the current coding block and the best matching block in its reference picture is represented by a Motion Vector (MV). Each divided block has corresponding motion information to be transmitted to a decoding end. If the MVs of each block are coded and transmitted independently, especially divided into small-sized blocks, a considerable number of bits are consumed.

In order to reduce the number of bits used to encode motion information, h.264/AVC uses spatial correlation between adjacent macroblocks to predict motion information of a current block to be encoded from motion information of adjacent encoded blocks, and then encodes a prediction difference. This effectively reduces the number of bits representing motion information. Based on this, in the process of coding the MV of the current macroblock, the h.264/AVC firstly predicts the MV of the current macroblock by using the MVs of the adjacent coded blocks, and then codes the difference value (denoted as mvd (motion Vector difference)) between the predicted value (denoted as mvp (motion Vector prediction)) of the MV and the true estimate value of the MV, thereby effectively reducing the number of coding bits of the MV.

At present, in various application scenarios with strict requirements on motion detection, such as tennis tracking, tennis player motion tracking, and the like, not only a high-precision image acquisition mechanism but also a high-precision motion vector detection mechanism are required, however, precision and computation of the motion vector detection mechanism are mutually restricted, and dynamic equalization needs to be performed on the images and even the videos according to specific contents of the images, and obviously, a corresponding technical scheme is lacked at present.

Disclosure of Invention

The invention has at least the following two key points:

(1) detecting the definition and the number of objects of the tennis court image acquired by the eagle eye acquisition mechanism, and determining the number of image frames required for executing motion vector detection in the current tennis court image based on the detection results of the definition and the number of the objects so as to achieve dynamic balance between the encoding operand and the encoding reliability;

(2) and respectively detecting the definition and the number of objects of the tennis court image acquired by the eagle eye acquisition mechanism by adopting a targeted detection mechanism.

According to an aspect of the present invention, there is provided an adaptive motion vector detection system, the system including:

the vector detection device is connected with the frame number selection mechanism and is used for selecting a plurality of target areas with the total current use frame number from the target area corresponding to the current acquisition image frame to a plurality of target areas respectively corresponding to a plurality of previous acquisition moments on the basis of the current use frame number so as to detect each motion vector of each motion target in the target area corresponding to the current acquisition image frame;

the encoding execution equipment is connected with the vector detection equipment and is used for encoding a target area corresponding to the acquired image frame at the current moment based on each detected motion vector of each motion target so as to obtain encoded data to be transmitted;

the eagle eye acquisition mechanism is arranged on a tennis match field and used for carrying out ultra-clear image acquisition at uniform time intervals on the tennis match field so as to obtain a plurality of continuous acquired image frames;

the band-pass filtering equipment is connected with the eagle eye acquisition mechanism and is used for performing band-pass filtering processing on each received acquired image frame to obtain a field processing image;

the field identification device is connected with the band-pass filtering device and used for identifying a target area only comprising a tennis field from the field processing image based on the imaging characteristics of the tennis field;

the cutting processing equipment is connected with the field recognition equipment and is used for cutting a target area from the field processing image so as to obtain a plurality of continuous target areas corresponding to a plurality of continuous acquisition image frames respectively;

the definition analysis equipment is connected with the cutting processing equipment and is used for extracting the definition of a target area corresponding to the collected image frame at the current moment to be output as the current definition;

the quantity identification device is connected with the definition analysis device and is used for identifying the quantity of the objects existing in the target area corresponding to the collected image frame at the current moment so as to obtain the quantity of the current objects;

the frame number selection mechanism is respectively connected with the definition analysis equipment and the number identification equipment and is used for determining the corresponding current using frame number based on the current definition and the current object number;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the higher the current definition is, the less the corresponding current using frame number is determined;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the smaller the number of current objects, the smaller the number of determined corresponding current usage frames.

The self-adaptive motion vector detection system is reliable in principle and convenient to operate and control. On the basis of intelligent detection of the definition and the number of objects of the field image, the number of image frames required by executing motion vector detection in the field image is set in a self-adaptive mode, and therefore coding computation and coding reliability are considered.

Detailed Description

An embodiment of the adaptive motion vector detection system of the present invention will be described in detail below.

Image compression coding can be divided into two categories: one type of compression is reversible, i.e., the original image can be completely restored from the compressed data without loss of information, which is called lossless compression coding; another type of compression is irreversible, i.e. the original image cannot be completely restored from the compressed data, and there is a certain loss of information, which is called lossy compression coding.

Under the condition of meeting the requirement of certain fidelity, the image data is transformed, coded and compressed, redundant data is removed, and the data quantity required by representing the digital image is reduced, so that the image can be conveniently stored and transmitted. That is, a technique of expressing the original pixel matrix with a small amount of data with loss or without loss is also called image coding.

For example, the BMP is an image file format independent of hardware devices, and is very widely used. The method adopts a bit mapping storage format, and does not adopt any other compression except that the image depth is selectable, so that the space occupied by the BMP file is large. The image depth of the BMP file can be selected from lbit, 4bit, 8bit and 24 bit. When the BMP file stores data, the scanning mode of the image is from left to right, from bottom to top. Since the BMP file format is a standard for exchanging data related to a graph in the Windows environment, the BMP image format is supported by the graphics image software running in the Windows environment. A typical BMP image file consists of three parts: the bitmap file header data structure comprises information such as the type and display content of the BMP image file; and the bitmap information data structure comprises information such as width, height and compression method of the BMP image, definition color and the like.

Motion vectors are one of the key parameters required to perform image coding, and are particularly suitable for coding moving objects within an image. At present, in various application scenarios with strict requirements on motion detection, such as tennis tracking, tennis player motion tracking, and the like, not only a high-precision image acquisition mechanism but also a high-precision motion vector detection mechanism are required, however, precision and computation of the motion vector detection mechanism are mutually restricted, and dynamic equalization needs to be performed on the images and even the videos according to specific contents of the images, and obviously, a corresponding technical scheme is lacked at present.

In order to overcome the defects, the invention builds a self-adaptive motion vector detection system, and can effectively solve the corresponding technical problem.

An adaptive motion vector detection system according to an embodiment of the present invention includes:

the vector detection device is connected with the frame number selection mechanism and is used for selecting a plurality of target areas with the total current use frame number from the target area corresponding to the current acquisition image frame to a plurality of target areas respectively corresponding to a plurality of previous acquisition moments on the basis of the current use frame number so as to detect each motion vector of each motion target in the target area corresponding to the current acquisition image frame;

the encoding execution equipment is connected with the vector detection equipment and is used for encoding a target area corresponding to the acquired image frame at the current moment based on each detected motion vector of each motion target so as to obtain encoded data to be transmitted;

the eagle eye acquisition mechanism is arranged on a tennis match field and used for carrying out ultra-clear image acquisition at uniform time intervals on the tennis match field so as to obtain a plurality of continuous acquired image frames;

the band-pass filtering equipment is connected with the eagle eye acquisition mechanism and is used for performing band-pass filtering processing on each received acquired image frame to obtain a field processing image;

the field identification device is connected with the band-pass filtering device and used for identifying a target area only comprising a tennis field from the field processing image based on the imaging characteristics of the tennis field;

the cutting processing equipment is connected with the field recognition equipment and is used for cutting a target area from the field processing image so as to obtain a plurality of continuous target areas corresponding to a plurality of continuous acquisition image frames respectively;

the definition analysis equipment is connected with the cutting processing equipment and is used for extracting the definition of a target area corresponding to the collected image frame at the current moment to be output as the current definition;

the quantity identification device is connected with the definition analysis device and is used for identifying the quantity of the objects existing in the target area corresponding to the collected image frame at the current moment so as to obtain the quantity of the current objects;

the frame number selection mechanism is respectively connected with the definition analysis equipment and the number identification equipment and is used for determining the corresponding current using frame number based on the current definition and the current object number;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the higher the current definition is, the less the corresponding current using frame number is determined;

wherein determining a corresponding current number of frames used based on the current definition and the current number of objects comprises: the smaller the number of current objects, the smaller the number of determined corresponding current usage frames.

Next, the detailed structure of the adaptive motion vector detection system of the present invention will be further described.

In the adaptive motion vector detection system:

the band-pass filtering device, the field recognition device, the cutting processing device, the definition analysis device, the number recognition device and the frame number selection mechanism are all arranged in a control room of a tennis match field.

In the adaptive motion vector detection system, further comprising:

and the data temporary storage mechanism is respectively connected with the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

In the adaptive motion vector detection system:

the data temporary storage mechanism is used for storing temporary storage data of the band-pass filter equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism respectively.

In the adaptive motion vector detection system:

the data temporary storage mechanism is also used for storing configuration parameters of the band-pass filter equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism respectively.

In the adaptive motion vector detection system, further comprising:

and the uninterrupted power supply is respectively connected with the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

In the adaptive motion vector detection system:

the uninterrupted power supply is used for respectively providing required power supply voltage for the band-pass filtering equipment, the field identification equipment, the cutting processing equipment, the definition analysis equipment, the quantity identification equipment and the frame number selection mechanism.

In the adaptive motion vector detection system:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition to be output comprises the following steps: and extracting the definition of each image block in a target area corresponding to the acquired image frame at the current moment to be used as each reference definition.

In the adaptive motion vector detection system:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition output further comprises the following steps: and sequencing the reference definitions, and removing the highest value and the lowest value to obtain more than one definition to be processed.

In the adaptive motion vector detection system:

the step of extracting the definition of the target area corresponding to the collected image frame at the current moment to serve as the current definition output further comprises the following steps: performing mean value calculation on the more than one definition to be processed to obtain the current definition;

the method for identifying the number of the objects in the target area corresponding to the acquired image frame at the current moment to obtain the current number of the objects comprises the following steps: and removing a background area in a target area corresponding to the acquired image frame at the current moment, and outputting the number of the remaining foreground image blocks as the number of the current objects.

In addition, in the adaptive motion vector detection system, the data temporary storage mechanism may be implemented using an FPM DRAM. FPM DRAM (Fast Page Mode RAM): fast page mode memory. Is a memory that was commonly used during time 486 (also used as video memory). The parameters of the FPM DRAM are as follows: 72 lines, 5V voltage, 32bit bandwidth and basic speed of more than 60 ns. His read cycle begins with the triggering of a row in the DRAM array and then moves to the location indicated by the memory address, i.e., contains the desired data. The first message must be validated and stored to the system in preparation for the next cycle. This introduces a "wait state" because the CPU must wait for the memory to complete one cycle foolproof. One important reason for the widespread use of FPM is that it is a standard and safe product.

While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.