Detection tracking algorithm optimization method based on multi-core heterogeneous platform

A heterogeneous platform, detection and tracking technology, applied in computing, image data processing, instruments, etc., can solve the problems of slow computing speed, affecting the computing speed and accuracy of detection and tracking, reducing computing requirements, increasing computing efficiency, The effect of improving computational efficiency

Pending Publication Date: 2020-01-17
杭州博雅鸿图视频技术有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are some problems in the existing detection and tracking algorithms: the calculation is carried out on the traditional CPU platform, and there is a problem of slow calculation speed; detection and tracking may detect objects without semantics
These problems affect the calculation speed and accuracy of detection and tracking

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
  • Detection tracking algorithm optimization method based on multi-core heterogeneous platform
  • Detection tracking algorithm optimization method based on multi-core heterogeneous platform
  • Detection tracking algorithm optimization method based on multi-core heterogeneous platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0058] Such as figure 1 As shown, the optimization implementation of the measurement and tracking algorithm disclosed in the present invention is based on a multi-core heterogeneous platform. The multi-core heterogeneous platform mainly includes: P6, C5, two DSP cores, GC620 graphics, and Zhongtian C-SKY CPU ( CK860). The task of calculation on each core is figure 1 As described in detail in P6, P6 mainly performs the calculation of filt...

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

The invention provides a detection tracking algorithm optimization method based on a multi-core heterogeneous platform. The method comprises the following steps: firstly, zooming an input 1920 * 1080high-definition image into two output resolution images by adopting a GC620 graphic accelerator, namely a resolution of 300 * 300 and a resolution of 300 * 300 for detection of a detector; 2, zoomingto the resolution of 720 * 576 for tracking on the zoomed image by the tracker. By use of the frame-level pipeline of object detection and the object-level pipeline of target tracking, the calculationefficiency is improved. The cache object information is stored in the on-chip SRAM, so that the calculation efficiency is improved. A multi-core heterogeneous platform is used for carrying out distributed calculation on a filter module on C5 and P6, so that the calculation efficiency is improved. And meanwhile, by utilizing the KCF response value, the calculation requirement of the classificationfilter is further reduced.

Description

Technical field [0001] The present invention relates to a detection and tracking algorithm optimization hardware implementation in the field of deep learning, in particular to a detection and tracking algorithm optimization method based on a multi-core heterogeneous platform. Background technique [0002] The detection and tracking technology based on deep learning is the foundation of various application technologies. For example, applications such as the number of heads in public buses and school buses, face recognition and other applications that are widely used now require detection and tracking technology. However, the existing detection and tracking algorithms have some problems: the calculation is performed on the traditional CPU platform, and the calculation speed is slow, and the detection and tracking may identify and detect non-semantic objects. These problems affect the calculation speed and accuracy of detection and tracking. [0003] How to use a multi-core heterogen...

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 Applications(China)
IPC IPC(8): G06T7/246
CPCG06T7/248G06T2207/10016G06T2207/20084
Inventor 黄晓峰吴飞红王升堂黄仁强郑龙飞陈科殷海兵贾惠柱
Owner 杭州博雅鸿图视频技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap