Requirements for the operation of the Neural tracker and its sub-detectors are given in the table:
Object images | - The detected object must be clearly distinguishable by the human eye
- Width and height of objects in the image must not exceed 75% of the frame size
- When you use a neural filter, the minimum width or height of an object must be at least 5% of the width/height of the frame
- The image isn't noisy and not distorted by the artifacts of the compression algorithm
- The duration of the object visibility is at least six frames
- Between two frames, an object must move in the direction of a distance not exceeding its size. This condition is necessary for the correct calculation of the object track
- The minimum value of pixel density per meter is observed:
Image resolution | Object type | Minimum pixel density per meter (ratio of the object width in pixels to the object width in meters) | Minimum object size in pixels, width x height | Ratio of the object width to the frame width as a percentage |
---|
1920x1080 | Human | 55 | ~25x105 | ~3% | 1280x720 | Human | 35 | ~17x70 | ~3% | 640x360 | Human | 17 | ~10x42 | ~3% | 1920x1080 | Light vehicle (2 axles) | 55 | ~354x300 | ~20% | 1280x720 | Light vehicle (2 axles) | 35 | ~240x205 | ~20% | 640x360 | Light vehicle (2 axles) | 17 | ~132x112 | ~20% |
|