Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses
Visual browse and exploration in motion capture data take resource acquisition as a human–computer interaction problem, and it is an essential approach for target motion search. This paper presents a progressive schema which starts from pose browse, then locates the interesting region and then switc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/18/5224 |
| _version_ | 1827706286767079424 |
|---|---|
| author | Songle Chen Xuejian Zhao Bingqing Luo Zhixin Sun |
| author_facet | Songle Chen Xuejian Zhao Bingqing Luo Zhixin Sun |
| author_sort | Songle Chen |
| collection | DOAJ |
| description | Visual browse and exploration in motion capture data take resource acquisition as a human–computer interaction problem, and it is an essential approach for target motion search. This paper presents a progressive schema which starts from pose browse, then locates the interesting region and then switches to online relevant motion exploration. It mainly addresses three core issues. First, to alleviate the contradiction between the limited visual space and ever-increasing size of real-world database, it applies affinity propagation to numerical similarity measure of pose to perform data abstraction and obtains representative poses of clusters. Second, to construct a meaningful neighborhood for user browsing, it further merges logical similarity measures of pose with the weight quartets and casts the isolated representative poses into a structure of phylogenetic tree. Third, to support online motion exploration including motion ranking and clustering, a biLSTM-based auto-encoder is proposed to encode the high-dimensional pose context into compact latent space. Experimental results on CMU’s motion capture data verify the effectiveness of the proposed method. |
| first_indexed | 2024-03-10T16:21:19Z |
| format | Article |
| id | doaj.art-3a042b34aa6d4f70aa119d0058a0b0c3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:21:19Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3a042b34aa6d4f70aa119d0058a0b0c32023-11-20T13:36:19ZengMDPI AGSensors1424-82202020-09-012018522410.3390/s20185224Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware PosesSongle Chen0Xuejian Zhao1Bingqing Luo2Zhixin Sun3Key Lab of Broadband Wireless Communication and Sensor Network Technology of Ministry of Education, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaKey Lab of Broadband Wireless Communication and Sensor Network Technology of Ministry of Education, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaJiangsu Key Laboratory of Big Data Security & Intelligent Processing, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaKey Lab of Broadband Wireless Communication and Sensor Network Technology of Ministry of Education, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaVisual browse and exploration in motion capture data take resource acquisition as a human–computer interaction problem, and it is an essential approach for target motion search. This paper presents a progressive schema which starts from pose browse, then locates the interesting region and then switches to online relevant motion exploration. It mainly addresses three core issues. First, to alleviate the contradiction between the limited visual space and ever-increasing size of real-world database, it applies affinity propagation to numerical similarity measure of pose to perform data abstraction and obtains representative poses of clusters. Second, to construct a meaningful neighborhood for user browsing, it further merges logical similarity measures of pose with the weight quartets and casts the isolated representative poses into a structure of phylogenetic tree. Third, to support online motion exploration including motion ranking and clustering, a biLSTM-based auto-encoder is proposed to encode the high-dimensional pose context into compact latent space. Experimental results on CMU’s motion capture data verify the effectiveness of the proposed method.https://www.mdpi.com/1424-8220/20/18/5224motion capture datapose browsemotion explorationauto-encoder |
| spellingShingle | Songle Chen Xuejian Zhao Bingqing Luo Zhixin Sun Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses Sensors motion capture data pose browse motion exploration auto-encoder |
| title | Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses |
| title_full | Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses |
| title_fullStr | Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses |
| title_full_unstemmed | Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses |
| title_short | Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses |
| title_sort | visual browse and exploration in motion capture data with phylogenetic tree of context aware poses |
| topic | motion capture data pose browse motion exploration auto-encoder |
| url | https://www.mdpi.com/1424-8220/20/18/5224 |
| work_keys_str_mv | AT songlechen visualbrowseandexplorationinmotioncapturedatawithphylogenetictreeofcontextawareposes AT xuejianzhao visualbrowseandexplorationinmotioncapturedatawithphylogenetictreeofcontextawareposes AT bingqingluo visualbrowseandexplorationinmotioncapturedatawithphylogenetictreeofcontextawareposes AT zhixinsun visualbrowseandexplorationinmotioncapturedatawithphylogenetictreeofcontextawareposes |