Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet
The application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/11/3440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129492746436608 |
|---|---|
| author | Meng Lv Haoting Liu Mengmeng Wang Dongyang Wang Haiguang Li Xiaofei Lu Zhenhui Guo Qing Li |
| author_facet | Meng Lv Haoting Liu Mengmeng Wang Dongyang Wang Haiguang Li Xiaofei Lu Zhenhui Guo Qing Li |
| author_sort | Meng Lv |
| collection | DOAJ |
| description | The application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on mid-infrared images for all-weather surveillance. The approach integrates the Image Timing Features–Gaussian Mixture Model (ITF-GMM) and Convolutional-UNet (Con-UNet) to improve the accuracy of target detection. First, a robust background modelling, i.e., the ITF-GMM, is proposed. Unlike the basic Gaussian Mixture Model (GMM), the proposed model dynamically adjusts the learning rate according to the content difference between adjacent frames and optimizes the number of Gaussian distributions through time series histogram analysis of pixels. Second, a segmentation framework based on Con-UNet is developed to improve the feature extraction ability of UNet. In this model, the maximum pooling layer is replaced with a convolutional layer, addressing the challenge of limited training data and improving the network’s ability to preserve spatial features. Finally, an integrated computation strategy is designed to combine the outputs of ITF-GMM and Con-UNet at the pixel level, and morphological operations are performed to refine the segmentation results and suppress noises, ensuring clearer object boundaries. The experimental results show the effectiveness of proposed approach, achieving a precision of 96.92%, an accuracy of 99.87%, an intersection over union (IOU) of 94.81%, and a recall of 97.75%. Furthermore, the proposed algorithm meets real-time processing requirements, confirming its capability to enhance small-target detection in complex outdoor environments and supporting the automation of grassland monitoring and enforcement. |
| format | Article |
| id | doaj-art-01569cda0e9b47c2ba2a4d18cf668081 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-01569cda0e9b47c2ba2a4d18cf6680812025-08-20T02:32:57ZengMDPI AGSensors1424-82202025-05-012511344010.3390/s25113440Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNetMeng Lv0Haoting Liu1Mengmeng Wang2Dongyang Wang3Haiguang Li4Xiaofei Lu5Zhenhui Guo6Qing Li7Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaBeijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaBeijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaNational Key Laboratory of Human Factors Engineering, China Astronaut Research and Training Center, Beijing 100094, ChinaJiuquan Satellite Launch Center, Jiuquan 732750, ChinaJiuquan Satellite Launch Center, Jiuquan 732750, ChinaJiuquan Satellite Launch Center, Jiuquan 732750, ChinaBeijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaThe application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on mid-infrared images for all-weather surveillance. The approach integrates the Image Timing Features–Gaussian Mixture Model (ITF-GMM) and Convolutional-UNet (Con-UNet) to improve the accuracy of target detection. First, a robust background modelling, i.e., the ITF-GMM, is proposed. Unlike the basic Gaussian Mixture Model (GMM), the proposed model dynamically adjusts the learning rate according to the content difference between adjacent frames and optimizes the number of Gaussian distributions through time series histogram analysis of pixels. Second, a segmentation framework based on Con-UNet is developed to improve the feature extraction ability of UNet. In this model, the maximum pooling layer is replaced with a convolutional layer, addressing the challenge of limited training data and improving the network’s ability to preserve spatial features. Finally, an integrated computation strategy is designed to combine the outputs of ITF-GMM and Con-UNet at the pixel level, and morphological operations are performed to refine the segmentation results and suppress noises, ensuring clearer object boundaries. The experimental results show the effectiveness of proposed approach, achieving a precision of 96.92%, an accuracy of 99.87%, an intersection over union (IOU) of 94.81%, and a recall of 97.75%. Furthermore, the proposed algorithm meets real-time processing requirements, confirming its capability to enhance small-target detection in complex outdoor environments and supporting the automation of grassland monitoring and enforcement.https://www.mdpi.com/1424-8220/25/11/3440mid-infrared imageimage segmentationGaussian Mixture Model (GMM)UNetgrassland monitoring |
| spellingShingle | Meng Lv Haoting Liu Mengmeng Wang Dongyang Wang Haiguang Li Xiaofei Lu Zhenhui Guo Qing Li Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet Sensors mid-infrared image image segmentation Gaussian Mixture Model (GMM) UNet grassland monitoring |
| title | Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet |
| title_full | Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet |
| title_fullStr | Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet |
| title_full_unstemmed | Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet |
| title_short | Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet |
| title_sort | small scale multi object segmentation in mid infrared image using the image timing features gaussian mixture model and convolutional unet |
| topic | mid-infrared image image segmentation Gaussian Mixture Model (GMM) UNet grassland monitoring |
| url | https://www.mdpi.com/1424-8220/25/11/3440 |
| work_keys_str_mv | AT menglv smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT haotingliu smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT mengmengwang smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT dongyangwang smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT haiguangli smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT xiaofeilu smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT zhenhuiguo smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet AT qingli smallscalemultiobjectsegmentationinmidinfraredimageusingtheimagetimingfeaturesgaussianmixturemodelandconvolutionalunet |