- Tytuł:
- Systematic analysis and review of video object retrieval techniques
- Autorzy:
-
Ghuge, C. A.
Prakash, V. Chandra
Ruikar, Sachin D. - Powiązania:
- https://bibliotekanauki.pl/articles/2050246.pdf
- Data publikacji:
- 2020
- Wydawca:
- Polska Akademia Nauk. Instytut Badań Systemowych PAN
- Tematy:
-
video object retrieval
computer vision
deep learning
fuzzy-based techniques
machine learning
query-based techniques
graph-based techniques - Opis:
- Video object retrieval is a promising research direction, developing in the recent years, and the current video object retrieval strategies are used for visualizing, digitizing, modeling, and retrieving the objects especially in graphics and in architectural design. The research performed led to the design of proficient video object retrieval techniques. Yet, although, a number of algorithms had been devised for tracking objects, the problems persist in enhancing the performance, for instance – with regard to non-rigid objects. In this review article we provide a detailed survey of 50 research papers presenting the suggested video object retrieval methodologies, based on approaches such as deep learning techniques, graph-based techniques, query-based techniques, feature-based techniques, fuzzybased techniques, machine learning-based techniques, distance metric learning-based technique, and also other ones. Moreover, analysis and discussion are presented concerning the year of publication, employed methodology, evaluation metrics, accuracy range, adopted framework, datasets utilized, and the implementation tool. Finally, the research gaps and issues related to various proposed video object retrieval schemes are presented for guiding the researchers towards improved contributions to the video object retrieval methods.
- Źródło:
-
Control and Cybernetics; 2020, 49, 4; 471-498
0324-8569 - Pojawia się w:
- Control and Cybernetics
- Dostawca treści:
- Biblioteka Nauki
Artykuł