Object detection apparatus, object detection method and object detection program
First Claim
1. An object detection apparatus which detects a movable object in a region around a vehicle from a time series of images including at least a first and second image obtained through a camera mounted on the vehicle, the apparatus comprising:
- a feature point extraction unit which extracts a first set of feature point contained in a feature region of the first image and a second set of feature point contained in a feature region of the second image;
a correspondence degree computation unit which;
creates a combination set of pairs of feature points by pairing each feature point from the first set with each feature point of the second set,computes a degree of correspondence for each pair of the feature points in the combination set, andreduces the combination set to a corresponding pairs set that includes the pairs from the combination set having the highest computed degree of correspondence for each feature point of the first set; and
a detection unit which detects the movable object on the basis of the degree of correspondence computed by the correspondence degree computation unit.
1 Assignment
0 Petitions
Accused Products
Abstract
An object detection apparatus and method for accurately detecting a movable object in a region around a vehicle from a time series of images obtained through a camera mounted on the vehicle by eliminating the influence of the movement of the camera through simple processing, and a program for making a computer execute processing in the apparatus. The object detection apparatus has a feature point extraction unit which extracts a feature point contained in a feature region of each image in the time series of images obtained through a camera mounted on the vehicle, a correspondence degree computation unit which computes the degree of correspondence for each pair of the feature points, wherein one of the feature points in the each pair is each of one or more of the feature points extracted by the feature point extraction unit from one of two images taken by the camera at different times, and another of the feature points in the each pair is each of a plurality of the feature points extracted by the feature point extraction unit from another of the two images, and a detection unit which detects the movable object on the basis of the degree of correspondence computed by the correspondence degree computation unit.
16 Citations
6 Claims
-
1. An object detection apparatus which detects a movable object in a region around a vehicle from a time series of images including at least a first and second image obtained through a camera mounted on the vehicle, the apparatus comprising:
-
a feature point extraction unit which extracts a first set of feature point contained in a feature region of the first image and a second set of feature point contained in a feature region of the second image; a correspondence degree computation unit which; creates a combination set of pairs of feature points by pairing each feature point from the first set with each feature point of the second set, computes a degree of correspondence for each pair of the feature points in the combination set, and reduces the combination set to a corresponding pairs set that includes the pairs from the combination set having the highest computed degree of correspondence for each feature point of the first set; and a detection unit which detects the movable object on the basis of the degree of correspondence computed by the correspondence degree computation unit. - View Dependent Claims (2, 3, 4, 5)
-
-
6. An object detection method for detecting a movable object in a region around a vehicle from a time series of images including at least a first and second image obtained through a camera mounted on the vehicle, the method comprising:
-
a feature point extraction step of extracting a first set of feature points contained in a feature region of the first image and a second set of feature point contained in a feature region of the second image; a correspondence degree computation step of; creating a combination set of pairs of feature points by pairing each feature point from the first set with each feature point of the second set, computing a degree of correspondence for each pair of feature points in the combination set, and reducing the combination set to a corresponding pairs set that includes the pairs from the combination set having the highest computed degree of correspondence for each feature point of the first set; and a detection step of detecting the movable object on the basis of the degree of correspondence computed in the correspondence degree computation step.
-
Specification