Detecting anomalous events to trigger the uploading of video to a video storage server

A computer program product for triggering the uploading of video from a subset of cameras of a plurality of cameras implemented in a vehicle, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

• monitor video or image data captured by the plurality of cameras;
• analyze the monitored video or image data for objects, patterns, or motions within respective fields of view of the plurality of cameras;
• store pixel-based classification rules in the computer readable storage medium;
• store video uploading rules that identify a subset of the plurality of cameras for which video should be uploaded in the computer readable storage medium;
• detect an anomalous event using the analyzed monitored video or image data and the stored pixel-based classification rules to identify the anomalous event from the video or image data, wherein the anomalous event is defined by a particular set of objects, patterns, or motions and relates to a collision or a road hazard;
• determine the subset of cameras of the plurality of cameras that were used to detect the anomalous event and that captured the video or image data having objects, patterns, or motions consistent with the anomalous event and captured from a field of view facing and associated with the anomalous event;
• and
• upload video captured by only the subset of cameras of the plurality of cameras to a video storage server.

A system comprising:

• a CPU, a computer readable memory and a computer readable storage medium associated with a computing device;
• program instructions to monitor video or image data captured by a plurality of cameras implemented within a vehicle;
• program instructions to analyze the monitored video or image data for objects, patterns, or motions within respective fields of view of the plurality of cameras;
• program instructions to monitor vehicle information associated with the vehicle;
• program instructions to store pixel-based classification rules in the computer readable memory;
• program instructions to store video uploading rules that identify a subset of the plurality of cameras for which video should be uploaded in the computer readable memory;
• program instructions to detect an anomalous event using the analyzed monitored video or image data and the monitored vehicle information using the stored pixel-based classification rules to identify the anomalous event from the video or image data, wherein the detecting the anomalous event includes detecting a satisfaction of criteria defining the anomalous event, wherein the anomalous event is defined by a particular set of objects, patterns, or motions and relates to a collision or a road hazard;
• program instructions to determine the subset of the plurality of cameras of the plurality of cameras that were used to detect the anomalous event and that captured the video or image data having objects, patters, or motions consistent with the anomalous event and captured from a field of view facing and associated with the anomalous event;
• and
• program instructions to upload video captured by only the subset of cameras of the plurality of cameras within a particular time window to a video storage server,
• wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.