# US 11,308,641 B1 · Oncoming car detection using lateral emirror cameras > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,641 B1 - Document ID: US11308641B1 - Status: Granted - Kind: B1 - Application number: 16/722,131 - Filed: 2019-12-20 - Granted: 2022-04-19 - Earliest claimed: 2019-12-20 - Assignees: Ambarella International LP - Applicants: Ambarella International LP - Inventors: Pier Paolo Porta; Shimon Pertsel - Web page: https://patentgrep.com/patent/US11308641B1 ## CPC - B60R 1/25: to the sides of the vehicle - G06T 7/74: {involving reference images or patches} - B60R 1/04: mounted inside vehicle {(B60R1/025, B60R1/08 take precedence)} - B60R 1/06: mounted on vehicle exterior {(B60R1/025, B60R1/08 take precedence)} - B60R 1/26: to the rear of the vehicle - B60R 11/04: Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06T 7/292: Multi-camera tracking - G06T 7/593: from stereo images - G06T 7/60: Analysis of geometric attributes - G06T 7/73: using feature-based methods - B60R 2011/004: {outside the vehicle} - B60R 2300/105: using multiple cameras - B60R 2300/20: characterised by the type of display used - B60R 2300/8066: for monitoring rearward traffic - G06T 2207/10016: Video; Image sequence - G06T 2207/10021: Stereoscopic video; Stereoscopic image sequence - G06T 2207/10024: Color image - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30261: Obstacle - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An apparatus including an interface and a processor. The interface may be configured to receive first video frames of a first field of view captured by a first capture device and second video frames of a second field of view captured by a second capture device. The first capture device and the second capture device may have a symmetrical orientation with respect to a vehicle. The fields of view may have an overlapping region. The processor may be configured to select the capture devices to operate as a stereo pair of cameras based on the symmetrical orientation, receive the video frames from the interface, detect an object located in the overlapping region, perform a comparison operation on the object based on the symmetrical orientation with respect to the video frames and determine a distance of the object from the vehicle in response to the comparison operation. ## Claims ### Claim 1 An apparatus comprising: an interface configured to receive (i) first pixel data of a first field of view captured by a first capture device and (ii) second pixel data of a second field of view captured by a second capture device, wherein (a) said first capture device and said second capture device have a symmetrical orientation with respect to a center line dividing a left half and right half of a vehicle and (b) said first field of view and said second field of view have an overlapping region; and a processor configured to (i) select said first capture device and said second capture device to operate as a stereo pair of cameras based on said symmetrical orientation, (ii) receive said first pixel data and said second pixel data from said interface, (iii) process said first pixel data arranged as a first plurality of video frames and said second pixel data arranged as a second plurality of video frames, (iv) detect an object located in said overlapping region, (v) perform a comparison operation on said object based on said symmetrical orientation with respect to (a) said first plurality of video frames and (b) said second plurality of video frames and (vi) determine a distance of said object from said vehicle in response to said comparison operation. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein when said object is closer to said vehicle than said overlapping region, said processor is further configured to (i) perform an analysis of a plurality of video frames and (ii) determine said distance and a relative velocity of said object with respect to said vehicle in response to (a) said analysis and (b) a physical width that was previously measured when said object was in said overlapping region. ### Claim 3 (depends on 1) The apparatus according to claim 1, wherein (i) said first capture device and said second capture device are two of a plurality of capture devices connected to said interface and (ii) said processor is configured to select any two capture devices from said plurality of capture devices to operate as said stereo pair of cameras only if said two capture devices have said symmetrical orientation. ### Claim 4 (depends on 1) The apparatus according to claim 1, wherein said comparison operation is implemented by a disparity hardware engine of said processor. ### Claim 5 (depends on 1) The apparatus according to claim 1, wherein said symmetrical orientation comprises (i) said first capture device located on a driver side of said vehicle, (ii) said second capture device located on a passenger side of said vehicle and (iii) said first capture device and said second capture device both located an equal distance from a rear of said vehicle. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein at least one of said first plurality of video frames and said second plurality of video frames are also used to generate an output for a display. ### Claim 7 (depends on 6) The apparatus according to claim 6, wherein said display is implemented as an electronic mirror. ### Claim 8 (depends on 1) The apparatus according to claim 1, wherein said stereo pair of cameras is a virtual stereo pair of cameras created by said processor by selecting from a plurality of capture devices implemented by said vehicle. ### Claim 9 (depends on 1) The apparatus according to claim 1, wherein said distance is used by said processor to detect a potential rear collision. ### Claim 10 (depends on 1) The apparatus according to claim 1, wherein said symmetrical orientation comprises (i) said first capture device located on an outermost location of a first side of said vehicle and directed behind said vehicle, (ii) said second capture device located on an outermost location of a second side of said vehicle and directed behind said vehicle, (iii) said first capture device and said second capture device both located an equal distance from a rear of said vehicle and (iv) said overlapping region is located behind said vehicle. ### Claim 11 (depends on 10) The apparatus according to claim 10, wherein (i) said outermost location of said first side of said vehicle is a driver side mirror, (ii) said outermost location of said second side of said vehicle is a passenger side mirror. ### Claim 12 (depends on 11) The apparatus according to claim 11, wherein (i) said first capture device and said second capture device have a native functionality and (ii) selecting said first capture device and said second capture device to operate as said stereo pair of cameras adds a secondary function to said native functionality. ### Claim 13 An apparatus comprising: an interface configured to receive (i) first pixel data of a first field of view captured by a first capture device and (ii) second pixel data of a second field of view captured by a second capture device, wherein (a) said first capture device and said second capture device have a symmetrical orientation with respect to a vehicle and (b) said first field of view and said second field of view have an overlapping region; and a processor configured to (i) select said first capture device and said second capture device to operate as a stereo pair of cameras based on said symmetrical orientation, (ii) receive said first pixel data and said second pixel data from said interface, (iii) process said first pixel data arranged as a first plurality of video frames and said second pixel data arranged as a second plurality of video frames, (iv) detect an object located in said overlapping region, (v) perform a comparison operation on said object based on said symmetrical orientation with respect to (a) said first plurality of video frames and (b) said second plurality of video frames and (vi) determine a distance of said object from said vehicle in response to said comparison operation, wherein when said object is closer to said vehicle than said overlapping region, said processor is further configured to (i) perform an analysis of a plurality of video frames and (ii) determine said distance and a relative velocity of said object with respect to said vehicle in response to (a) said analysis and (b) a physical width that was previously measured when said object was in said overlapping region. ### Claim 14 (depends on 13) The apparatus according to claim 13, wherein said overlapping region is located a pre-determined distance from said vehicle. ### Claim 15 (depends on 14) The apparatus according to claim 14, wherein said pre-determined distance is 15 meters behind said vehicle. ### Claim 16 (depends on 14) The apparatus according to claim 14, wherein said processor is further configured to measure said physical width of said object in response to (a) said comparison operation and (b) said pre-determined distance. ### Claim 17 (depends on 13) The apparatus according to claim 13, wherein (i) said plurality of video frames each provide a monocular view and (ii) said processor determines said distance and said relative velocity with more accuracy than using said monocular view alone by using said monocular view with (a) said physical width that was previously measured and (b) learning. ### Claim 18 (depends on 17) The apparatus according to claim 17, wherein said plurality of video frames are (i) said first plurality of video frames or (ii) said second plurality of video frames. ### Claim 19 (depends on 17) The apparatus according to claim 17, wherein said plurality of video frames are captured by a third capture device configured to capture a third field of view.