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

System and method for detecting objects in a digital image, and system and method for rescoring object detections

a technology of object detection and digital image, applied in the field of system and method for detecting objects in digital image, and system and method for rescoring object detection, can solve the problem that conventional nms is doomed to sacrifice precision or recall independent of its parameter

Inactive Publication Date: 2020-06-18
TOYOTA MOTOR EUROPE +1
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent text describes a system that uses a neural network to learn non-maximum suppression (NMS) to overcome limitations in conventional NMS processing. This system can adapt to different data distributions and make tradeoffs based on the data, resulting in improved accuracy. Additionally, the system can perform non-maximum suppression without needing image content or decisions from other algorithms.

Problems solved by technology

When objects are close-by, conventional NMS is doomed to sacrifice precision or recall independent of its parameter.

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
  • System and method for detecting objects in a digital image, and system and method for rescoring object detections
  • System and method for detecting objects in a digital image, and system and method for rescoring object detections
  • System and method for detecting objects in a digital image, and system and method for rescoring object detections

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104]Reference will now be made in detail to exemplary embodiments of the disclosure, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

[0105]FIG. 1 shows a block diagram of a system 10 with an object detector 1 and a rescoring system 2 (i.e. a system for rescoring object detections) according to embodiments of the present disclosure. The system may have various further functions, e.g. may be a robotic system or a camera system. It may further be integrated in a vehicle.

[0106]The system 10 may comprise an electronic circuit, a processor (shared, dedicated, or group), a combinational logic circuit, a memory that executes one or more software programs, and / or other suitable components that provide the described functionality. In other words, system 10 may be a computer device. The system may be connected to a memory, which may store data, e.g. a computer...

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 relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises:generating a latent representation for each candidate window,updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, andgenerating the score for each candidate window based on its updated latent representationThe invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.

Description

FIELD OF THE DISCLOSURE[0001]The present disclosure is related to a system and a method for detecting objects in a digital image, and a system and a method for rescoring object detections.BACKGROUND OF THE DISCLOSURE[0002]Modern object detectors follow a three step recipe: (1) proposing a search space of windows (exhaustive by sliding window or sparser using proposals), (2) scoring / refining the window with a classifier / regressor, and (3) merging windows that might belong to the same object. This last stage is commonly referred to as “non-maximum suppression” (NMS), cf. e.g.:[0003]R. Girshick. Fast R-CNN. In ICCV, 2015,[0004]P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part-based models. PAMI, 2010, and[0005]W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed. Ssd: Single shot multibox detector. In ECCV, 2016,[0006]L. Wan, D. Eigen, and R. Fergus. End-to-end integration of a convolutional network, deformable parts mode...

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(United States)
IPC IPC(8): G06K9/62G06K9/32G06V10/25
CPCG06K9/623G06K9/6256G06K9/3241G06V10/25G06V10/82G06F18/214G06F18/2113
Inventor OLMEDA REINO, DANIELSCHIELE, BERNTHOSANG, JAN HENDRIKBENENSON, RODRIGO
Owner TOYOTA MOTOR EUROPE