Omnidirectional camera for use in police car event recording

Abstract

A system and method for an omnidirectional camera for use in recording events around a police vehicle is disclosed. The system and method include an omnidirectional camera and a digital processor for processing the omnidirectional images captured by the omnidirectional camera. The digital processor may be operable to locate one or more regions of interests disposed within the omnidirectional images. A recordable medium is also disclosed for storing at least some of the captured images.

What is claimed is: 
     
         1 . A system for capturing and storing images, the system comprising:
 an omnidirectional camera mounted to a vehicle and operable to capture an omnidirectional image of a scene in a field of view of the omnidirectional camera;   a digital processor coupled to the omnidirectional camera and operable to receive the captured omnidirectional image;   the digital processor being operable to locate an area of interest from the scene and define a first subset of the omnidirectional image corresponding to the area of interest as a region of interest and a second subset of the omnidirectional image mutually exclusive of the first subset;   a data-storage device coupled to the digital processor and operable to receive and store the first subset at a first resolution; and   the digital processor being operable to perform at least one of the following:
 discard the second subset; and 
 save the second subset at a second resolution lower than the first resolution. 
   
     
     
         2 . The system of  claim 1 , wherein the field of view of the omnidirectional camera is a 360-degree field of view. 
     
     
         3 . The system of  claim 1 , wherein the field of view of the omnidirectional camera is less than 360 degrees. 
     
     
         4 . The system of  claim 1 , comprising:
 a signal-generating device disposed within the scene; and   wherein the digital processor is operable to utilize a signal-detection algorithm to define the region of interest based at least in part on one or more signals received from the signal-generating device.   
     
     
         5 . The system of  claim 4 , wherein the signal-generating device comprises a wireless microphone. 
     
     
         6 . The system of  claim 1 , wherein the digital processor is operable to utilize a gaze-estimation algorithm to define the region of interest based at least in part on a direction a person is looking. 
     
     
         7 . The system of  claim 1 , wherein the digital processor is operable to utilize an object-detection algorithm to define the region of interest. 
     
     
         8 . The system of  claim 1 , comprising:
 an optical target disposed in the scene; and   wherein the digital processor is operable to utilize an optical-target detection algorithm to define the region of interest.   
     
     
         9 . The system of  claim 1 , wherein the digital processor defines the region of interest based in at least partial dependence on a user input. 
     
     
         10 . A method of capturing and storing images, the method comprising:
 providing an omnidirectional camera mounted to a vehicle and operable to capture an omnidirectional image of a scene in a field of view of the omnidirectional camera;   transmitting the omnidirectional image to a digital processor coupled to the omnidirectional camera;   locating, via the digital processor, an area of interest from the scene;   defining, via the digital processor, at least one region of interest within the omnidirectional image corresponding to the area of interest, the at least one region of interest corresponding to a first subset of the omnidirectional image;   storing the first subset at a first resolution in a data-storage device coupled to the digital processor; and   performing a step selected from the group consisting of:
 storing a second subset of the omnidirectional image at a second resolution in the data-storage device, the first resolution being greater than the second resolution; and 
 discarding the second subset of the omnidirectional image. 
   
     
     
         11 . The method of  claim 10 , wherein the field of view of the omnidirectional camera is a 360-degree field of view. 
     
     
         12 . The method of  claim 10 , wherein the field of view of the omnidirectional camera is less than 360 degrees. 
     
     
         13 . The method of  claim 10 , wherein the second subset is mutually exclusive of the first subset. 
     
     
         14 . The method of  claim 10 , wherein the at least one region of interest corresponds to an area of the scene immediately surrounding a law enforcement officer. 
     
     
         15 . The method of  claim 10 , comprising:
 coupling one or more antennae to the digital processor;   detecting, via at least one of the one or more antennae and the digital processor, a signal from a wireless device;   determining, by the digital processor, from what direction the signal came; and   using the determined direction to define the at least one region of interest.   
     
     
         16 . The method of  claim 10 , comprising:
 detecting, via the digital processor, a location of an object disposed in the field of view of the omnidirectional camera; and   defining the at least one region of interest via the detected location.   
     
     
         17 . The method of  claim 16 , wherein the location of the object is detected in at least partial dependence on a pattern of motion of the object. 
     
     
         18 . The method of  claim 10 , comprising:
 estimating a direction in which a person is looking; and   defining the at least one region of interest via the estimated direction.   
     
     
         19 . The method of  claim 10 , wherein the at least one region of interest is defined based in at least partial dependence on user input. 
     
     
         20 . A method of capturing and storing images, the method comprising:
 providing a 360-degree camera mounted inside a police vehicle and operable to capture a 360-degree image of a scene in a field of view of the 360-degree camera;   transmitting the 360-degree image to a digital processor coupled to the 360-degree camera;   locating, via the digital processor, an area of the scene containing an object of interest;   automatically defining a region of interest within the 360-degree image corresponding to the area of the scene containing the object of interest;   compressing to a first resolution a first subset of the omnidirectional image corresponding to the region of interest;   compressing to a second resolution a second subset of the omnidirectional image, the second subset being mutually exclusive to the first subset and the second resolution being lower than the first resolution; and   storing the first subset and the second subset in a storage medium coupled to the digital processor.