A combined grammar for object detection and pose estimation

被引:0
|
作者
Chen, Yao-Dong [1 ]
Li, Ren-Fa [1 ]
Li, Shi-Ying [1 ]
Huang, Xin [1 ]
Xie, Guo-Qi [1 ]
机构
[1] College of Computer Science and Electronic Engineering, Hunan University, Changsha,410082, China
来源
Jisuanji Xuebao/Chinese Journal of Computers | 2014年 / 37卷 / 10期
关键词
Object recognition - Computer vision;
D O I
10.3724/SP.J.1016.2014.02206
中图分类号
学科分类号
摘要
Consider that the limitation of part-based models on the description of object categories, we propose a discriminative grammar model. The model, which has powerful description ability and extensibility, can represent general objects and deal with common recognition tasks. We define two instantiations of the grammar model for object detection and pose estimation and then discuss the differences and similarities between them. Viewed from application background and current research methods, there is great complementarity in object detection and pose estimation. This paper further introduces a novel grammar that is constructed by combining two single-task grammars using a set of discriminative symbols. There are two characteristics for the combined grammar. First, it supports joint detection and pose estimation. Second, it can improve the detection performance of both tasks. For learning grammar parameters with weak supervision we utilize a structural SVM with latent variables. We compare the combined grammar with part-based models in single-task scenario and multiple-task scenario. The evaluated results demonstrate that the proposed grammar outperforms the state-of-the-art detection models and pose estimation models.
引用
收藏
页码:2206 / 2217
相关论文
共 50 条
  • [41] Depth Based Object Detection from Partial Pose Estimation of Symmetric Objects
    Barnea, Ehud
    Ben-Shahar, Ohad
    COMPUTER VISION - ECCV 2014, PT V, 2014, 8693 : 377 - 390
  • [42] SIFT-Cloud-Model for Object Detection and Pose Estimation with GPGPU Acceleration
    Nakada, Takahiro
    Kagami, Satoshi
    Mizoguchi, Hiroshi
    IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, : 1748 - 1753
  • [43] Feasibility Research on Fish Pose Estimation Based on Rotating Box Object Detection
    Lin, Bin
    Jiang, Kailin
    Xu, Zhiqi
    Li, Feiyi
    Li, Jiao
    Mou, Chaoli
    Gong, Xinyao
    Duan, Xuliang
    FISHES, 2021, 6 (04)
  • [44] OBJECT RECOGNITION AND POSE ESTIMATION BASED ON COMBINED USE OF PROJECTION HISTOGRAMS AND SURFACE FITTING
    Ahola, Jari M.
    Heikkila, Tapio
    PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2017, VOL 9, 2017,
  • [45] Object Detection and Pose Estimation Using CNN in Embedded Hardware for Assistive Technology
    Demby's, Jacket
    Gao, Yixiang
    Shafiekhani, Ali
    DeSouza, Guilherme N.
    2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 3165 - 3171
  • [46] POINTVOTENET: ACCURATE OBJECT DETECTION AND 6 DOF POSE ESTIMATION IN POINT CLOUDS
    Hagelskjaer, Frederik
    Buch, Anders Glent
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 2641 - 2645
  • [47] Towards an Open-Source Benchmark for Underwater Object Detection and Pose Estimation
    Saksvik, Ivar Bjorgo
    Weydahl, Hakon
    Teigland, Hakon
    Alcocer, Alex
    Hassani, Vahid
    2023 IEEE UNDERWATER TECHNOLOGY, UT, 2023,
  • [48] Articulated Part-based Model for Joint Object Detection and Pose Estimation
    Sun, Min
    Savarese, Silvio
    2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 723 - 730
  • [49] 3D Pose Estimation for Object Detection in Remote Sensing Images
    Liu, Jin
    Gao, Yongjian
    SENSORS, 2020, 20 (05)
  • [50] CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation
    Gupta, Kartik
    Petersson, Lars
    Hartley, Richard
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 2758 - 2766