A system includes a processor to capture a first image of a scene by a first imaging device of the array of imaging devices, capture a second image of the scene by a second imaging device of the array of imaging devices, perform image analysis of the first image and the second image and determining that an object is present in the first image and the object is present in the second image, the first image representing a first perspective of the object and the second image representing a second perspective of the object different from the first perspective of the object, classify the object with a classification based on a list of known objects and weight an object portion of the first image and an object portion of the second image based on the classification, compress the first image and the second image based on the weighting, encode the first image and the second image as multi-perspective image data, and store the multi-perspective image data in the non-transitory computer-readable medium based on the classification.