Where am I: Place instance and category recognition using spatial PACT

被引:0
|
作者
Wu, Jianixn [1 ]
Rehg, James M. [1 ]
机构
[1] Georgia Inst Technol, Coll Comp, Sch Interact Comp, Atlanta, GA 30332 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce spatial PACT (Principal component Analysis of Census Transform histograms), a new representation for recognizing instances and categories of places or scenes. Both place instance recognition ("I am in Room 113") and category recognition ("I am in an office") have been widely researched. Features that have different discriminative power/invariance tradeoff have been used separately for the two tasks. PACT captures local structures of an image through the Census Transform (CT), while large-scale structures are captured by the strong correlation between neighboring CT values and the histogram. The PCA operation ignores noise in the histogram distribution, computes important "primitive shapes", and results in a compact representation. Spatial PACT, a spatial pyramid of PACT, further incorporates global structures in the image. Our experiments demonstrate that spatial PACT outperforms the current state-of-the-art in several place and scene recognition, and shape matching datasets. Besides, spatial PACT is easy to implement. It has nearly no parameter to tune, and evaluates extremely fast.
引用
收藏
页码:2221 / 2228
页数:8
相关论文
共 27 条
  • [1] Spatial multi-scale gradient orientation consistency for place instance and Scene category recognition
    Gao, Changxin
    Sang, Nong
    Huang, Rui
    [J]. INFORMATION SCIENCES, 2016, 372 : 84 - 97
  • [2] 'This place where I am happy'
    Colby, Joan
    [J]. SOUTH DAKOTA REVIEW, 2007, 45 (02): : 42 - 43
  • [3] Where am I now? Distinct roles for parahippocampal and retrosplenial cortices in place recognition
    Epstein, Russell A.
    Parker, Whitney E.
    Feiler, Alana M.
    [J]. JOURNAL OF NEUROSCIENCE, 2007, 27 (23): : 6141 - 6149
  • [4] Recognition in Ultrasound Videos: Where Am I?
    Kwitt, Roland
    Vasconcelos, Nuno
    Razzaque, Sharif
    Aylward, Stephen
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2012, PT III, 2012, 7512 : 83 - 90
  • [5] Where am I? Scene recognition for mobile robots using audio features
    Chu, Selina
    Narayanan, Shrikanth
    Kuo, C. -C. Jay
    Mataric, Maja J.
    [J]. 2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS, 2006, : 885 - 888
  • [6] Where am I? Creating spatial awareness in unmanned ground robots using SLAM: A survey
    Dhiman, Nitin Kumar
    Deodhare, Dipti
    Khemani, Deepak
    [J]. SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2015, 40 (05): : 1385 - 1433
  • [7] Where am I? Creating spatial awareness in unmanned ground robots using SLAM: A survey
    NITIN KUMAR DHIMAN
    DIPTI DEODHARE
    DEEPAK KHEMANI
    [J]. Sadhana, 2015, 40 : 1385 - 1433
  • [8] WHERE AM I? Spatial Cognition Inside Building Information Models
    Pelosi, Antony
    [J]. PROCEEDINGS OF THE 22ND INTERNATIONAL CONFERENCE ON COMPUTER-AIDED ARCHITECTURAL DESIGN RESEARCH IN ASIA (CAADRIA 2017): PROTOCOLS, FLOWS AND GLITCHES, 2017, : 643 - 652
  • [9] Affect and Spatial Experiences of Migration in Karen Campbell's This Is Where I Am
    Rodriguez Alvarez, Andrea
    [J]. ENGLISH STUDIES, 2018, 99 (08) : 960 - 971
  • [10] Where am I? Who am I? The Relation Between Spatial Cognition, Social Cognition and Individual Differences in the Built Environment
    Proulx, Michael J.
    Todorov, Orlin S.
    Aiken, Amanda Taylor
    de Sousa, Alexandra A.
    [J]. FRONTIERS IN PSYCHOLOGY, 2016, 7