Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods for object detection

A target detection and target technology, applied in the field of target detection, can solve the problems of high memory bandwidth, increasing the size of intermediate data elements, etc.

Active Publication Date: 2021-11-19
TEXAS INSTR INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, computing the integral image reduces the number of computations but increases the intermediate data element size, which also requires high memory bandwidth

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods for object detection
  • Systems and methods for object detection
  • Systems and methods for object detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Unless specifically indicated, the drawings are not necessarily drawn to scale and such drawings are merely exemplary in nature.

[0019] refer to figure 1 , shows an image 100 formed from a plurality of image pixels. For the i-th image pixel, the i+1(x) and i-1(x) are adjacent image pixels in the x direction, and the i+1(y) and i-1(y) are in Neighboring image pixels in the y direction. Each image pixel has an intensity and a gradient, where the gradient of the i-th image pixel has magnitude MG i and direction θ i . The gradient direction θ of the i-th image pixel i Expressed by the following formula:

[0020] θ i =tan -1 the y i / x i (1)

[0021] where x i = the horizontal gradient of the i-th pixel, and y i = the vertical gradient of the i-th pixel.

[0022] In one example, the horizontal gradient of the ith pixel has magnitude and direction "positive" or "negative" and is represented by:

[0023] x i =I(x i-1 )-I(x i+1 ) (2)

[0024] where I(x i-...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

In the described example, a method of detecting an object in an image includes computing ( 802 ) one or more feature planes of one or more types for each image pixel of the image. Cells are defined (804) in the image, where each cell includes first through nth numbers of pixels. The initial position of each unit in the image in the horizontal and vertical directions is an integer multiple of a predefined horizontal and vertical step size, respectively. One or more feature plane sums of one or more types are computed (806) for each cell. Determining (808) a feature vector for an image portion of the image based on the set of feature plane sums, and comparing (810) the feature vector to a corresponding target classifier to detect a feature vector in the image portion of the image The existence of the corresponding target.

Description

technical field [0001] The present invention generally relates to object detection, such as detection of pedestrians and other objects from vehicles. Background technique [0002] Today, vehicles are equipped with object detectors to detect objects such as pedestrians on the road and provide warning / brake assistance to the driver. Object detectors employ cameras to capture video / images in front of and around the vehicle, and apply image processing techniques therein for identifying obstacles and pedestrians in front of and around the vehicle. [0003] Existing target detectors use the target detection technique based on the histogram of oriented gradients (HOG), in which the image is divided into multiple blocks (blocks), and the magnitude of the pixel gradient in each block in any direction is counted to form The HOG of the image. Machine learning methods apply recognition and classification techniques to HOG in order to efficiently identify pedestrians and predefined obj...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/46G06K9/62G06V10/56
CPCG06V10/507G06V10/758G06V10/56
Inventor K·A·德萨班M·马修P·K·斯瓦米
Owner TEXAS INSTR INC