Pedestrian detection device and pedestrian detection method

• US 8,131,079 B2
• Filed: 11/09/2007
• Issued: 03/06/2012
• Est. Priority Date: 11/09/2006
• Status: Expired due to Fees

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Hayasaka, Shoichi, Hara, Yoshimasa, Sato, Hironori, Fukamachi, Hideo, Sawaki, Toshio
• Primary Examiner(s): Bhatnagar, Anand
• Application Number:
  US12/308,553
• Publication Number:
  US 20100067740A1
• Time in Patent Office: 1,579 Days
• Field of Search: 382/100, 382/103, 382/106, 382/107, 382/115, 382/117, 382/118, 382/181, 382/190, 382/195, 382/199, 382/203, 382/206, 382/217, 382/218, 382/219, 701/1, 701/200, 701/300, 701/301, 701/302, 351/204
• US Class Current: 382/181
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A near-infrared night vision device to which a pedestrian detection device is applied includes a near-infrared projector, a near-infrared camera, a display and an ECU. By executing programs, the ECU constitutes a pedestrian candidate extraction portion and a determination portion. The pedestrian candidate extraction portion extracts pedestrian candidate regions from near-infrared images. The determination portion normalizes the sizes and the brightnesses of the pedestrian candidates extracted by the pedestrian candidate extraction portion, and then computes the degrees of similarity between the normalized pedestrian candidates. The determination portion determines that a pedestrian candidate having two or more other pedestrian candidates whose degree of similarity with the pedestrian candidate is greater than or equal to a predetermined value is not a pedestrian.

Claims

1. A pedestrian detection device comprising:

pedestrian candidate extraction portion that extracts a pedestrian candidate from a picked-up image; and

determination portion that finds a degree of similarity between pedestrian candidates if a plurality of pedestrian candidates are extracted by the pedestrian candidate extraction portion, and that determines that a pedestrian candidate whose degree of similarity with another pedestrian candidate is greater than or equal to a predetermined value is not a pedestrian.

2. The pedestrian detection device according to claim 1, wherein

the determination portion determines that the pedestrian candidate having two or more other pedestrian candidates whose degrees of similarity with said pedestrian candidate are greater than or equal to the predetermined value is not a pedestrian.

3. The pedestrian detection device according to claim 1, wherein

the pedestrian candidate extraction portion normalizes a size and/or a brightness of the pedestrian candidate extracted, and

the determination portion finds the degree of similarity between pedestrian candidates normalized in the size and/or brightness by the pedestrian candidate extraction portion.

4. The pedestrian detection device according to claim 3, wherein

the determination portion finds the degree of similarity between pedestrian candidates by using a Euclidean distance based on the brightness differences in terms of individual pixels between the pedestrian candidates normalized in the size and/or the brightness.

5. The pedestrian detection device according to claim 1, wherein

the determination portion finds the degree of similarity between pedestrian candidates by using a brightness histogram of pixels of the pedestrian candidates.

6. A pedestrian detection method comprising:

extracting a pedestrian candidate from a picked-up image; and

finding a degree of similarity between pedestrian candidates, and determining that a pedestrian candidate whose degree of similarity with another pedestrian candidate is greater than or equal to a predetermined value is not a pedestrian, when a plurality of pedestrian candidates are extracted by extraction of the pedestrian candidate, wherein

at least one of the steps of extracting and finding is performed using an Electronic Control Device (ECU).