Evaluation of video activity localizations integrating quality and quantity measurements


Creative Commons License

Wolf C., Lombardi E., Mille J., Celiktutan O., Jiu M., Dogan E., ...Daha Fazla

COMPUTER VISION AND IMAGE UNDERSTANDING, cilt.127, ss.14-30, 2014 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 127
  • Basım Tarihi: 2014
  • Doi Numarası: 10.1016/j.cviu.2014.06.014
  • Dergi Adı: COMPUTER VISION AND IMAGE UNDERSTANDING
  • Sayfa Sayıları: ss.14-30

Özet

Evaluating the performance of computer vision algorithms is classically done by reporting classification error or accuracy, if the problem at hand is the classification of an object in an image, the recognition of an activity in a video or the categorization and labeling of the image or video. If in addition the detection of an item in an image or a video, and/or its localization are required, frequently used metrics are Recall and Precision, as well as ROC curves. These metrics give quantitative performance values which are easy to understand and to interpret even by non-experts. However, an inherent problem is the dependency of quantitative performance measures on the quality constraints that we need impose on the detection algorithm. In particular, an important quality parameter of these measures is the spatial or spatio-temporal overlap between a ground-truth item and a detected item, and this needs to be taken into account when interpreting the results.