VISION BASED PEDESTRIAN AND CYCLIST DETECTION METHOD

• US 20150161447A1
• Filed: 12/09/2013
• Published: 06/11/2015
• Est. Priority Date: 12/09/2013
• Status: Active Grant

• Current Assignee: National Chung-Shan Institute of Science and Technology
• Original Assignee: Chung-Shan Institute of Science & Technology Armaments Bureau MND (Government of The Republic of China)
• Inventors: Hu, Shao-Chung, Fu, Li-Chen, Hsiao, Pei-Yung, Wu, Cheng-En, Chan, Yi-Ming
• Granted Patent: US 9,087,263 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/77 using statistical methods
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A vision based pedestrian and cyclist detection method includes receiving an input image, calculating a pixel value difference between each pixel and the neighbor pixels thereof, quantifying the pixel value difference as a weight of pixel, proceeding statistics for the pixel value differences and the weights, determining intersections of the statistics as a feature of the input image, classifying the feature into human feature and non-human feature, confirming the human feature belonging to cyclist according to the spatial relationship between the human feature and the detected two-wheeled vehicle, and retaining one detection result for each cyclist by suppressing other weaker spatial relationships between the human feature and the detected two-wheeled vehicle.

Claims

1. A vision based pedestrian and cyclist detection method, proceeded by a computing processor, comprising the following steps of:

receiving an input image containing at least one human and at least one two-wheeled vehicle;

calculating a pixel value difference between each pixel and the neighbor pixels thereof within the input image;

quantifying the pixel value difference of each pixel, and defined as a weight of the pixel;

proceeding statistics for the pixel value differences and the weights;

determining intersections of the statistics as a feature of the input image;

classifying the feature into human feature and non-human feature;

proceeding a two-wheeled vehicle detection to the input image;

confirming whether the human feature is belonging to cyclist if when the spatial relationship between the human feature and the detected two-wheeled vehicle holds; and

retaining one detection result for each cyclist by suppressing other weaker spatial relationships between the human feature and the detected two-wheeled vehicle.

2. The vision based pedestrian and cyclist detection method as claimed in claim 1, wherein the pixel value difference is encoded as an 8-bit binary number.

3. The vision based pedestrian and cyclist detection method as claimed in claim 2, wherein the weight of the pixel is defined by a following formula:

4. The vision based pedestrian and cyclist detection method as claimed in claim 3, wherein the result of statistics is a set of histograms, each histogram is constructed according to the pixel value difference and the weight of pixel.

5. The vision based pedestrian and cyclist detection method as claimed in claim 4, wherein classifying the feature into human feature and non-human feature is achieved by a pre-trained linear supported vector machine (SVM) classifier.

6. The vision based pedestrian and cyclist detection method as claimed in claim 5, wherein the spatial relationship between the human feature and the detected two-wheeled vehicle is described by a horizontally geometric mean, a vertically geometric mean and a relative ratio, of the human feature and the detected two-wheeled vehicle.

7. The vision based pedestrian and cyclist detection method as claimed in claim 5, wherein the spatial relationship between the human feature and the detected two-wheeled vehicle is converted into a probability to be compared with a predetermined threshold to confirm whether the human feature belongs to cyclist.