Repeat occurrences of false alarms, combined with undetected events, can significantly deter end users from using video analytics. While these problems have decreased dramatically in recent years, the level of accuracy will depend on the intended application of the analytics. Therefore it is important first to have a common understanding of customer expectations. The following environmental and computational factors are important to understand when setting appropriate expectations.
Environmental factors have a tremendous influence over the performance of virtually all video analytics algorithms. There are six general environmental factors.
- Camera Angle: The angle of the camera can influence several factors used in video analytics, including perspective, occlusion, and segmentation of objects.
- Distance to Object: Pixel size of the object is an important element to video analytics. Most video analytics require a minimum pixel size (e.g. 15 x 15). Conversely, if the pixel sizes of the objects are too large, that too can distort the performance of the analytics (e.g. reflecting light into the camera).
- Lighting Level: Lighting can influence video analytics in a few ways. First, in order for video analytics to detect objects, there needs to be some minimum light available (unless infrared or thermal cameras are being used). Second, abrupt changes in lighting (e.g. opening of doors) can cause false conclusions.
- Degree of Activity: The degree of activity or “busyness” of an environment has influence over the performance of video analytics. Generally, the higher the level of activity, the more false conclusions will be drawn by the video analytics algorithm.
- Weather: The volatility and variance of weather (sun, rain, snow, wind, trees, clouds, shadows, etc.) can cause false conclusion for video analytics, especially in outdoor environments. Weather also has impact on video analytics in indoor environments where there exist large glass windows and doors and the mentioned conditions create changes to the scene viewed by the indoor camera.
- Backgrounds: The degree of change to the background of a camera view can impact the performance of video analytics. For instance, if the view of the camera includes a constantly moving escalator, this could result in false conclusions, and would be need to be taken into account when developing or installing a solution.
Video analytics algorithms can vary greatly on the amount of computational power needed to perform adequately. There are five general factors that influence performance.
- Processing Power: More CPU is required if for detecting small objects moving quickly. This is because the engine needs to run at a high resolution (detect small objects) and also at a high frame rate (track fast objects).
- Resolution: Normally you can record video at 4CIF, and do analysis at CIF which saves CPU. If you want to detect very small objects, you may have to run at 4CIF.
- Frame Rate: Most analytics engines need between 5 and 8 frames per second. Faster moving objects require higher FPS for tracking. Even left item detection analytics often use motion tracking to cut down on false positives.
- Hard Disk: If you want to be able to search through analyzed footage (eg objects moving near a car), you will need to store the XML metadata produced by the analytics engine. This is normally a negligible amount of HD.
- Memory: An analytics engine usually requires an additional 10MB to 100MB when run on a PC. Higher resolutions need more memory.