Multiple View and Multiple Object Processing in Wide-Angle Video Camera

Abstract

Methods and systems of transmitting a plurality of views from a video camera are disclosed. A multi object processing camera captures a wide-angle field of view in high resolution and a processing circuit executes a plurality of software tasks on a plurality of regions extracted from the wide-angle view. Multiple objects can be processed by the camera to detect various events, and the results of the processing transmitted to a base station. The camera removes the need for mechanical pan, tilt, and zoom apparatus by correcting distortions in the electronic image introduced by the wide-angle optical system and image sensor to electronically emulate the pan, tilt, and zoom movement.

1 - 30 . (canceled) 
     
     
         31 . A surveillance video camera, comprising:
 a wide-angle lens and image sensor system configured to generate a digital video image using a lens capturing an approximate hemispherical image data set, the digital video image optically distorted by the lens and sensor; and   a memory storing captured wide-angle video image frames or image frames of regions of interest and a programmable image processing circuit that accesses and processes the stored video image frames to perform at least one of the following tasks:
 correct optical distortions introduced by the lens and sensor; 
 execute movement and zoom operations on the digital video image by electronically manipulating the digital image data; 
 condition transmission of a partial set of images from the digital video image data based on the results of event detection; 
 validate results of a detection algorithm by another surveillance camera coupled to the surveillance camera; 
 autonomously identify a specific object among multiple monitored objects; 
 track an identified object; 
 communicate position and trajectory data of an identified object to at least one other surveillance camera; 
 receive position and trajectory data from another surveillance camera for an object; and 
 automatically track and monitor a specific object as it moves across the field of view of multiple the surveillance camera; and 
 designate at least one region of interest based on a software algorithm result. 
   
     
     
         32 . The surveillance camera of  claim 31 , further comprising a control circuit that transmits commands to the image processing circuit relating to the at least one region of interest, the image processing circuit responding to the commands with executed commanded movement to emulate a pan, tilt, or zoom movement to at least one specified region of interest. 
     
     
         33 . The surveillance camera of  claim 31 , further comprising a transmitting circuit transmitting desired region of interest images and the complete digital video image for simultaneous viewing, with each region of interest image and the complete digital video image scalable to different resolutions and controlled to emulate movement and zoom. 
     
     
         34 . The surveillance camera of  claim 31 , wherein a region of interest corresponds to a virtual camera addressed by a network address and controllable autonomously by the software in the surveillance camera and also from a base station using the network address. 
     
     
         35 . The surveillance camera of  claim 31 , wherein a software algorithm in the programmable image processing circuit performs at least one of:
 behavior detection;   motion detection;   smoke detection;   left package detection;   face recognition;   object detection; and   event detection.   
     
     
         36 . The surveillance camera of  claim 31 , wherein the programmable image processing circuit can execute movement and zoom commands while performing image analysis on the portions or the totality of the stored image video frame. 
     
     
         37 . The surveillance camera of  claim 31 , wherein the programmable image processing circuit can execute movement and zoom commands specific to at least one region of interest on a live video image feed while simultaneously performing image analysis on the portions or the totality of the stored image video frame. 
     
     
         38 . The surveillance camera of  claim 31 , wherein the programmable image processing circuit can have software to perform a task added or modified. 
     
     
         39 . A method of monitoring an area using a wide-angle digital video camera, comprising:
 capturing a digital video image using a lens providing an approximate hemispherical field of view and an image sensor to monitor an area, the digital video image distorted by the lens;   programming an image processing circuit to process the distorted electronic image video data to mathematically correct the distortion and perform at least one analysis algorithm on the image;   using an analysis algorithm result to autonomously designate at least one region of interest correlating to a generated virtual camera monitoring the individual region of interest within the digital video image;   monitoring multiple specific objects without losing surveillance of other multiple objects, the processing of the digital image including identifying an object and tracking the object among multiple objects;   correcting optical distortion to emulate a pan, tilt, or zoom command in a specified virtual camera; and   storing in a local storage at least one video image frame for later processing and analysis.   
     
     
         40 . The method of  claim 39 , further comprising the step of:
 modifying software on the processing circuit.   
     
     
         41 . The method of  claim 40 , wherein the software performs at least one of the following:
 correct optical distortions introduced by the lens and sensor;   execute movement and zoom operations on the digital video image by electronically manipulating the digital image data;   condition transmission of a partial set of images from the digital video image data based on the results of event detection;   validate results of a detection algorithm by another surveillance camera coupled to the surveillance camera;   autonomously identify a specific object among multiple monitored objects;   track an identified object among multiple objects;   communicate position and trajectory data of an identified object to at least one other surveillance camera;   receive position and trajectory data from another surveillance camera for an object; and   automatically track and monitor a specific object as it moves across the field of view of multiple the surveillance camera; and   designate at least one region of interest based on a software algorithm result.   
     
     
         42 . The method of  claim 39 , wherein the programmable image processing circuit performs at least one of the following analysis:
 behavior detection;   motion detection;   smoke detection;   left package detection;   face recognition;   object detection; and   event detection.   
     
     
         43 . The method of  claim 40 , wherein the virtual camera is designated by a network address and controllable autonomously by the software in the camera and also from a base station using the network address. 
     
     
         44 . A method of using a distorted image data from a wide-angle digital video camera, comprising the steps of:
 storing image data in a local memory accessible by an image processing circuit;   programming an image processing circuit to process image data to mathematically correct the distortion on at least one of live video feed image data or stored image data;   performing at least one analysis algorithm on the image data, the analysis performed on at least one of a live video feed or stored image data;   using an analysis algorithm result to autonomously designate at least one region of interest within the video image; and   monitoring multiple specific objects without losing surveillance of other multiple objects, the processing of the image data including identifying an object and tracking the object among multiple objects.   
     
     
         45 . The method of  claim 44 , further comprising the step of:
 correcting optical distortion to emulate a pan, tilt, or zoom command in a specified region of interest.   
     
     
         46 . The method of  claim 44 , further comprising the step of:
 modifying image processing software in the processing circuit.   
     
     
         47 . The method of  claim 44 , wherein the processing of image data can further comprise the steps of:
 correcting optical distortions introduced by a lens and sensor;   executing commanded movement and zoom operations on the digital video image by electronically manipulating the image data;   conditioning transmission of a partial set of images from the digital video image data based on the results of an algorithm;   validating results of a analysis algorithm by another video camera;   autonomously identifying a specific object among multiple monitored objects;   tracking an identified object among multiple objects;   communicating position and trajectory data of an identified object to at least one other video cameras;   receiving position and trajectory data from another surveillance camera for an object; and   automatically tracking and monitoring a specific object as it moves across the field of view of multiple the video cameras.   
     
     
         48 . The method of  claim 44 , wherein the programmable image processing circuit performs at least one of the following algorithm analysis:
 behavior detection;   motion detection;   smoke detection;   left package detection;   face recognition;   object detection; and   event detection.   
     
     
         49 . The method of  claim 40 , wherein the region of interest correlates to a virtual camera designated by a network address and controllable autonomously by the software in the video camera and also from a base station using the network address.