Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent object recognition system and control method based on depth learning

A smart object and recognition system technology, applied in the field of pattern recognition, can solve problems such as poor detection effect and failure of hidden objects, achieve good technical support, improve quality, and solve technical bottlenecks

Pending Publication Date: 2019-01-11
XIAN UNVERSITY OF ARTS & SCI
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the object detection process, the design based on the conventional visible light camera has poor detection effect on hidden objects, and at the same time, it will fail in the dark night environment and under the condition of occlusion.
Therefore, there are many technical bottlenecks in video object detection technology.

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
  • Intelligent object recognition system and control method based on depth learning
  • Intelligent object recognition system and control method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0030] Such as figure 1 As shown, the system of the present invention consists of DSP controller, FPGA controller, dual-port RAM memory, DDR3 memory, high-definition digital camera, infrared polarization lens, CCD image sensor, data communication interface module, WIFI controller, ultrasonic transmitter receiver, loudspeaker and power supply, in which the high-definition digital camera, infrared polarizing lens, and CCD image sensor are respectively connected to the dual-port RAM memory and the DSP controller, the dual-port RAM memory is respectively connected to the DSP controller and the FPGA controller, and the FPGA controller is respectively connected to the DSP The controller is connected to the DDR3 memory, and the DSP controller is electrically connected to the DDR3 memory. The DSP controller is also connected to the data communication interface module, WIFI controller, ultrasonic transmitter receiver and speaker respectively. The power supply is a rechargeable battery, ...

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 discloses an intelligent object recognition system and control method based on depth learning. The system comprises: a DSP controller, an FPGA control, a RAM memory, a DDR3 memory, an image acquisition module, an infrared polarized light imaging module, a data communication interface module, a WIFI Controller, an ultrasonic transmitter receiver, a loudspeaker and a power source. Theinvention adopts depth learning algorithm to realize object detection and target recognition, and realizes the algorithm on embedded hardware quickly, can better solve some technical bottlenecks in object detection and recognition, and provides better technical support for automatic driving, pedestrian detection, personal safety protection and intelligent monitoring.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a deep learning-based intelligent object recognition system and control method. Background technique [0002] Deep learning has brought huge improvements to object detection in images. Object detection is a more difficult task than object recognition. An image may contain multiple objects belonging to different categories. Object detection requires determining the location and category of each object. , however, the application of deep learning to video classification is far from mature. The image features obtained from ImageNet training can be directly and effectively applied to various image-related recognition tasks (such as image classification, image retrieval, object detection and image segmentation, etc.), and other different image test sets, with good Generalization performance. Large-scale training data sets need to be established (the latest da...

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): G06K9/40G06K9/46G06N3/08
CPCG06N3/08G06V10/30G06V10/50
Inventor 杨森林闫瞾张煜姬颖李喜龙崇鑫
Owner XIAN UNVERSITY OF ARTS & SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products