Towards Automated Learning of Object Detectors

被引：0
|
作者：
Ebner, Marc [1 ]
机构：
[1] Univ Tubingen, Wilhelm Schickard Inst Informat, Abt Rechnerarchitektur, D-72076 Tubingen, Germany
来源：
APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS | 2010年 / 6024卷
关键词：
EVOLUTIONARY; RECOGNITION; FILTERS;
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：
Recognizing arbitrary objects in images or video sequences is a difficult task for a computer vision system. We work towards automated learning of object detectors from video sequences (without user interaction). Our system uses object motion as an important cue to detect independently moving objects in the input sequence. The largest object is always taken as the teaching input, i.e. the object to be extracted. We use Cartesian Genetic Programming to evolve image processing routines which deliver the maximum output at the same position where the detected object is located. The graphics processor (GPU) is used to speed up the image processing. Our system is a step towards automated learning of object detectors.
引用
收藏
页码：231 / 240
页数：10
相关论文
共 50 条
  • [1] Automated Detection of Subsurface Defects Using Active Thermography and Deep Learning Object Detectors
    Lema, Dario G.
    Pedrayes, Oscar D.
    Usamentiaga, Ruben
    Venegas, Pablo
    Garcia, Daniel F.
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [2] Automated Model Hardening with Reinforcement Learning for On-Orbit Object Detectors with Convolutional Neural Networks
    Shi, Qi
    Li, Lu
    Feng, Jiaqi
    Chen, Wen
    Yu, Jinpei
    AEROSPACE, 2023, 10 (01)
  • [3] Joint learning of object and action detectors
    Kalogeiton, Vicky
    Weinzaepfel, Philippe
    Ferrari, Vittorio
    Schmid, Cordelia
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 2001 - 2010
  • [4] Unsupervised learning of object detectors for everyday scenes
    1600, Science and Engineering Research Support Society (07):
  • [5] Towards automated restructuring of object oriented systems
    Trifu, Adrian
    Reupke, Urs
    CSMR 2007: 11TH EUROPEAN CONFERENCE ON SOFTWARE MAINTENANCE AND REENGINEERING, PROCEEDINGS: SOFWARE EVOLUTION IN COMPLEX SOFTWARE INTENSIVE SYSTEMS, 2007, : 39 - +
  • [6] Towards toxic and narcotic medication detection with rotated object detectors
    Peng, Jiao
    Wang, Feifan
    Ma, Xiaochi
    Chen, Zichen
    Fu, Zhongqiang
    Hu, Yiying
    Zhou, Xinghan
    Wang, Lijun
    QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2023, 13 (04) : 2156 - 2166
  • [7] Incremental Learning of Object Detectors without Catastrophic Forgetting
    Shmelkov, Konstantin
    Schmid, Cordelia
    Alahari, Karteek
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 3420 - 3429
  • [8] Learning Efficient Binarized Object Detectors With Information Compression
    Wang, Ziwei
    Lu, Jiwen
    Wu, Ziyi
    Zhou, Jie
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (06) : 3082 - 3095
  • [9] Learning for Free: Object Detectors Trained on Synthetic Data
    MacKay, Charles Thane
    Moh, Teng-Sheng
    PROCEEDINGS OF THE 2021 15TH INTERNATIONAL CONFERENCE ON UBIQUITOUS INFORMATION MANAGEMENT AND COMMUNICATION (IMCOM 2021), 2021,
  • [10] How efficient deep-learning object detectors are?
    Miguel Soria, Luis
    Ortega, Francisco J.
    Alvarez-Garcia, Juan A.
    Velasco, Francisco
    Fernandez-Cerero, Damian
    NEUROCOMPUTING, 2020, 385 : 231 - 257
12345