Obstacle detection device
An obstacle detection device is provided, which includes a storage unit, a quasi-vertical edge detection module, an intersection determination module, a position determination module, and an obstacle detection module. The quasi-vertical edge detection module receives an input image and performs a quasi-vertical edge detection procedure on the input image to obtain a plurality of quasi-vertical edges. The intersection determination module determines whether the quasi-vertical edges intersect a predetermined virtual horizontal. If one of the quasi-vertical edges intersects the predetermined virtual horizontal, the position determination module determines whether an end of one of the quasi-vertical edges intersecting the predetermined virtual horizontal is located in a detection zone. If one end of one of the quasi-vertical edges intersecting the predetermined virtual horizontal is located in the detection zone, the obstacle detection module determines that an obstacle exists and issues a warning.
1. An obstacle detection device, comprising:
a storage unit at least storing an image;
a quasi-vertical edge detection module coupled to the storage unit to receive an input image and perform a quasi-vertical edge detection procedure on the input image to obtain a plurality of quasi-vertical edges;
an intersection determination module determining whether each of the quasi-vertical edges intersects a virtual horizontal served as a horizon line in the image and dividing the image into a above-horizon zone and a below-horizon zone;
a position determination module determining whether an end of one of the quasi-vertical edges intersecting the virtual horizontal is located in a detection zone according to position of the end of the one of the quasi-vertical edges and range of the detection zone if the one of the quasi-vertical edges intersects the virtual horizontal, wherein the detection zone is located within the below-horizon zone which is below the virtual horizontal; and
an obstacle detection module determining that an obstacle exists and issuing a warning if the end of the one of the quasi-vertical edges intersecting the virtual horizontal is located in the detection zone.
2. The obstacle detection device according to claim 1 , wherein the quasi-vertical edge detection module comprises a first direction edge detection and a second direction edge detection to obtain a plurality of first direction edges and a plurality of second direction edges and obtain the quasi-vertical edges according to an angle relationship between the first direction edges and the second direction edges.
3. The obstacle detection device according to claim 1 , wherein the quasi-vertical edge detection module groups the quasi-vertical edges that are close to each other.
4. The obstacle detection device according to claim 2 , wherein the first direction edge detection of the quasi-vertical edge detection module is a horizontal edge detection and the second direction edge detection is a vertical edge detection.
5. An obstacle detection device, comprising:
a storage unit at least storing a video stream comprising a plurality of images continuously captured during a tracking period;
a quasi-vertical edge detection module coupled to the storage unit to receive an input image of the video stream and perform a quasi-vertical edge detection procedure on the input image to obtain a plurality of quasi-vertical edges;
a quasi-vertical edge tracking module coupled to the quasi-vertical edge detection module and continuously tracking the quasi-vertical edges for the tracking period respectively;
a slope variation calculation module comparing a slope variation value of each of the quasi-vertical edges in the tracking period and determining whether the slope variation value is smaller than a threshold value, wherein the slope variation calculation module compares a slope of one of quasi-vertical edges in one of the images with another slope of another one of quasi-vertical edges corresponding to the one of quasi-vertical edges in another one of the images, so as to obtain the slope variation value of each of the quasi-vertical edges; and
an obstacle detection module determining that an obstacle exists and issuing a warning if one of the slope variation values is smaller than the threshold value.
6. The obstacle detection device according to claim 5 , wherein the quasi-vertical edge detection module comprises a first direction edge detection and a second direction edge detection to obtain a plurality of first direction edges and a plurality of second direction edges and obtain the quasi-vertical edges according to an angle relationship between the first direction edges and the second direction edges.
7. The obstacle detection device according to claim 5 , wherein the quasi-vertical edge detection module groups the quasi-vertical edges that are close to each other and have similar slopes.
8. The obstacle detection device according to claim 6 , wherein the first direction edge detection of the quasi-vertical edge detection module is a horizontal edge detection and the second direction edge detection is a vertical edge detection.
9. The obstacle detection device according to claim 1 , wherein the quasi-vertical edge detection module uses a ratio of a edge value of a horizontal direction and a edge value of the vertical direction to analyze the directionality of a plurality of edges, so as to obtain the quasi-vertical edges from the edges in the input image.