Detecting and classifying small objects in thermal imagery using a deep neural network

被引：0
|
作者：
Hemstrom, Fredrik [1 ]
Nasstrom, Fredrik [1 ]
Karlholm, Jorgen [1 ]
机构：
[1] Swedish Def Res Agcy, Dept Sensor Informat, SE-58330 Linkoping, Sweden
来源：
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN DEFENSE APPLICATIONS | 2019年 / 11169卷
关键词：
thermal imagery; object detection; deep learning;
D O I：
10.1117/12.2533252
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In recent years the rise of deep learning neural networks has shown great results in image classification. Most of the previous work focuses on classification of fairly large objects in visual imagery. This paper presents a method of detecting and classifying small objects in thermal imagery using a deep learning method based on a RetinaNet network. The result shows that a deep neural network with a relative small set of labelled images can be trained to classify objects in thermal imagery. Objects from classes with the most training examples (cars, trucks and persons) can with relative high confidence be classified given an object size of 32x32 pixels or smaller.
引用
收藏
页数：7
相关论文
共 50 条
  • [41] Classification of Citrus Crops using Satellite Multispectral Imagery and Deep Neural Network
    Camara-Guerra, Alvaro
    Artyounian-Vieyra, Cloe
    Gonzalez-Cuellar, Eder
    Trevino-Escamilla, Adriana
    Salazar-Garibay, Adan
    Hernandez-Gutierrez, Andres
    2024 16TH INTERNATIONAL CONFERENCE ON COMPUTER AND AUTOMATION ENGINEERING, ICCAE 2024, 2024, : 351 - 356
  • [42] A convolutional neural network for detecting sea turtles in drone imagery
    Gray, Patrick C.
    Fleishman, Abram B.
    Klein, David J.
    McKown, Matthew W.
    Bezy, Vanessa S.
    Lohmann, Kenneth J.
    Johnston, David W.
    METHODS IN ECOLOGY AND EVOLUTION, 2019, 10 (03): : 345 - 355
  • [43] A Deep Convolutional Neural Network for Detecting Volcanic Thermal Anomalies from Satellite Images
    Amato, Eleonora
    Corradino, Claudia
    Torrisi, Federica
    Del Negro, Ciro
    REMOTE SENSING, 2023, 15 (15)
  • [44] Occupancy Detection for Smart HVAC Efficiency in Building Energy: A Deep Learning Neural Network Framework using Thermal Imagery
    Acquaah, Yaa
    Steele, Jonathan B.
    Gokaraju, Balakrishna
    Tesiero, Raymond
    Monty, Gregory H.
    2020 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR): TRUSTED COMPUTING, PRIVACY, AND SECURING MULTIMEDIA, 2020,
  • [45] VEHICLE DETECTION IN THERMAL IMAGES USING DEEP NEURAL NETWORK
    Chang, Chin-Wei
    Srinivasan, Kathiravan
    Chen, Yung-Yao
    Cheng, Wen-Huang
    Hua, Kai-Lung
    2018 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP), 2018,
  • [46] Detection of small man-made objects in sector scan imagery using neural networks
    Perry, SW
    Guan, L
    OCEANS 2001 MTS/IEEE: AN OCEAN ODYSSEY, VOLS 1-4, CONFERENCE PROCEEDINGS, 2001, : 2108 - 2114
  • [47] Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network
    Kawarazuka, Kento
    Ogawa, Toru
    Tamura, Juntaro
    Nabeshima, Cota
    2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 2139 - 2145
  • [48] Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects
    Szymak, Piotr
    Gasiorowski, Marek
    NASE MORE, 2020, 67 (01): : 9 - 13
  • [49] A deep neural network for small object detection in complex environments with unmanned aerial vehicle imagery
    Jobaer, Sayed
    Tang, Xue-song
    Zhang, Yihong
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 148
  • [50] A neural-network-based approach to detecting rectangular objects
    Su, Mu-Chun
    Hung, Chao-Hsin
    NEUROCOMPUTING, 2007, 71 (1-3) : 270 - 283
12345