Pre-Trained Object Class Recognizers

OpenText may provide pre-trained recognizers that you can use with Media Server to recognize objects in images and videos.

The following recognizers are currently available, in the package MediaServerPretrainedModels_<VERSION>_COMMON.zip. When you download this package, ensure that <VERSION> matches the version of Media Server that you are using.

For information about how to import a recognizer into your training database, see Import a Recognizer.

Visual Analytics

To use the following recognizers, Media Server must be able to request a visual channel from your License Server.

  • ObjectClassRecognizer_Large_CommonObjects80.dat

    Recognizes 80 different types of common object.

    The object classes are: aeroplane, apple, backpack, banana, baseball bat, baseball glove, bear, bed, bench, bicycle, bird, boat, book, bottle, bowl, broccoli, bus, cake, car, carrot, cat, cell phone, chair, clock, cow, cup, diningtable, dog, donut, elephant, fire hydrant, fork, frisbee, giraffe, hair drier, handbag, horse, hot dog, keyboard, kite, knife, laptop, microwave, motorbike, mouse, orange, oven, parking meter, person, pizza, pottedplant, refrigerator, remote, sandwich, scissors, sheep, sink, skateboard, skis, snowboard, sofa, spoon, sports ball, stop sign, suitcase, surfboard, teddy bear, tennis racket, tie, toaster, toilet, toothbrush, traffic light, train, truck, tvmonitor, umbrella, vase, wine glass, zebra.

  • ObjectClassRecognizer_Small_CommonObjects80.dat

    Recognizes 80 different types of common object (the same classes as the corresponding large model). This recognizer prioritizes faster analysis and is likely to provide lower accuracy than the large model.

  • ObjectClassRecognizer_HeadAndShoulder.dat

    Recognizes people, in order to count them. This recognizer has been trained to detect only the head and shoulder region, which is useful when you want to count people in a crowded area.

Surveillance Analytics

To use the following recognizers, Media Server must be able to request a visual or surveillance channel from your License Server.

  • ObjectClassRecognizer_Large_Surveillance.dat

    Intended for tracking objects as part of a surveillance configuration. The object classes are: person, car, bicycle, truck, motorcycle, bus.

  • ObjectClassRecognizer_Small_Surveillance.dat

    Intended for tracking objects as part of a surveillance configuration. The object classes are the same as the corresponding large model: person, car, bicycle, truck, motorcycle, bus. This recognizer prioritizes faster analysis and is likely to provide lower accuracy than the large model.