Abstract: A vehicle periphery monitoring device is operable to recognize with high accuracy whether or not an object is a designated quadruped animal. According to the vehicle periphery monitoring device, for determining whether or not a first object region and a second object region correspond to the designated quadruped animal according to whether or not the aspect ratio of the first object region is equal to or greater 1, a plurality of the second object regions are extracted, and it is determined whether the ratio of the vertical dimension of the second object region to the vertical dimension of the first object region lies within the range of the ratio of the leg vertical dimension to the torso vertical dimension of a common designated quadruped animal.

Abstract: A vehicle periphery monitoring device is operable to report a high contact possibility between a vehicle and an object at an appropriate time or frequency according to the type of the object. When the object is determined to be a human being and the position of the object in real space is contained in a first contact determination area, a high contact possibility between the vehicle and the object is reported. On the other hand, when the object is determined to be a quadruped animal and the real spatial position of the object is contained in a second contact determination area, the corresponding report is made. The second contact determination area has an overlapped area that overlaps with the first contact determination area, and an overflowed area that has at least a part thereof overflowing from the first contact determination area.

Abstract: Provided is an apparatus capable of, even when an object is moving, measuring the position of the object at a high accuracy. According to a vehicle periphery monitoring apparatus (10), an enlargement factor relevant to when the degree of correlation between an enlarged local region (EB(?i)) obtained by enlarging a local region (B(k?1)) at a previous time (k?1) and a local region (B(k)) at a time (k) later than the previous time (k?1) becomes the maximum is calculated as a change rate (Rate(k)) of the size of the local region (B(k)). Based on the change rage (Rate(k)), it is possible to measure the distance (Z(k)) from a vehicle (1) to the object or the position (P(k)) at a high accuracy even when the object is moving.

Abstract: The present invention provides an automotive environment monitoring device to detect the existence of an object, a pedestrian or the like, with high accuracy even if one part of the object is overlapped with the background of an image obtained from an imaging unit mounted on the vehicle. An area where the object exists in the image obtained from an infrared camera (102) is set as a first area (A1i) and a lower portion of the first area (A1i) is set as a second area (A2i). A feature of the object is extracted with respect to the second area (A2i) and the object is identified based on the extracted feature. Thereby, even in the case where the first area (A1i) has been set but the feature of an upper part of the object can not be extracted due to the upper part of the object being overlapped with the background of the image, the object can still be identified with high accuracy by extracting the feature of a lower part of the object in the second area (A2i).

Abstract: A vehicle environment monitoring apparatus is equipped with a monitored object detecting unit 26 which detects an object having possibility of contact by applying an object detecting algorithm for short range when the distance calculated from data on one disparity by the first distance calculating unit 24 is equal to or less than a predetermined distance, and detects the object having possibility of contact by applying an object detecting algorithm for long range when the distance is longer than the predetermined distance, using the distance between the object and the vehicle calculated from a disparity gradient by the second distance calculating unit 25.

Abstract: An object type determination apparatus, an object type determination method, a vehicle, and a program for determining an object type, capable of accurately determining the type of the object by appropriately determining periodicity in movement of the object from images, are provided.

Abstract: The present invention provides an automotive environment monitoring device to detect the existence of an object, a pedestrian or the like, with high accuracy even if one part of the object is overlapped with the background of an image obtained from an imaging unit mounted on the vehicle. An area where the object exists in the image obtained from an infrared camera (102) is set as a first area (A1i) and a lower portion of the first area (A1i) is set as a second area (A2i). A feature of the object is extracted with respect to the second area (A2i) and the object is identified based on the extracted feature. Thereby, even in the case where the first area (A1i) has been set but the feature of an upper part of the object can not be extracted due to the upper part of the object being overlapped with the background of the image, the object can still be identified with high accuracy by extracting the feature of a lower part of the object in the second area (A2i).

Abstract: An object such as a person is extracted from images captured by cameras (2R, 2L) to determine the degree of vertical symmetry of the object (step 33). In the case where the degree of vertical symmetry is determined to be high, the object is determined to be other than a living body (step 33a). In the case where the degree of vertical symmetry is determined to be low, the object is determined likely to be a living body (step 33b). In the case where determined likely to be a living body, the object is further determined to be a predetermined kind of living body (for example, a person) or not based on the image of the object (steps 34 and 35). This allows an extremely reliable and simple determination of whether the type of the object extracted from the image captured by the camera is a living body such as a person.