Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation
Existing concealed objects detection methods in active millimeter wave (AMMW) images are mainly based on bounding boxes. In this paper, we consider the problem of precise localization of concealed objects in AMMW images with the use of semantic segmentation networks. To improve the performance of th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9133393/ |
| _version_ | 1818920692672888832 |
|---|---|
| author | Chongjian Wang Kehu Yang Xiaowei Sun |
| author_facet | Chongjian Wang Kehu Yang Xiaowei Sun |
| author_sort | Chongjian Wang |
| collection | DOAJ |
| description | Existing concealed objects detection methods in active millimeter wave (AMMW) images are mainly based on bounding boxes. In this paper, we consider the problem of precise localization of concealed objects in AMMW images with the use of semantic segmentation networks. To improve the performance of the detection and localization of concealed objects, we propose a method with two steps. In the first step, we build a two-class semantic segmentation network to segment concealed objects in pixels from the images with the complex human body background, while in the second step, we use connected components extraction to detect and localize concealed objects in the segmented image. To improve the performance of the detection and localization of small objects, the network we built is composed of stacked dilated convolution blocks to enlarge the receptive field while keeping the resolution of associated feature maps unchanged. In addition, we give a rule for design of the associated dilation rates and the expand-contract dilation (ECD) assignment strategy for the pattern of the dilation rates. In the numerical experiments, we use the universal evaluation metrics, such as the AP (average precision) @ IoU (Intersection over Union)=0.5 and mIoU (mean value of IoU) to evaluate the performance of precise localization. The experiment results show that our method outperforms the existing ones for precise object localization in AMMW images, where the improvement of the AP@0.5 is about 38% and that of the mIoU is about 27%. |
| first_indexed | 2024-12-20T01:25:48Z |
| format | Article |
| id | doaj.art-d7ad33569d5042a7915efdb08d0d991b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T01:25:48Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d7ad33569d5042a7915efdb08d0d991b2022-12-21T19:58:14ZengIEEEIEEE Access2169-35362020-01-01812124612125610.1109/ACCESS.2020.30072569133393Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic SegmentationChongjian Wang0https://orcid.org/0000-0003-0504-1808Kehu Yang1Xiaowei Sun2ISN Laboratory, Xidian University, Xi’an, ChinaISN Laboratory, Xidian University, Xi’an, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, ChinaExisting concealed objects detection methods in active millimeter wave (AMMW) images are mainly based on bounding boxes. In this paper, we consider the problem of precise localization of concealed objects in AMMW images with the use of semantic segmentation networks. To improve the performance of the detection and localization of concealed objects, we propose a method with two steps. In the first step, we build a two-class semantic segmentation network to segment concealed objects in pixels from the images with the complex human body background, while in the second step, we use connected components extraction to detect and localize concealed objects in the segmented image. To improve the performance of the detection and localization of small objects, the network we built is composed of stacked dilated convolution blocks to enlarge the receptive field while keeping the resolution of associated feature maps unchanged. In addition, we give a rule for design of the associated dilation rates and the expand-contract dilation (ECD) assignment strategy for the pattern of the dilation rates. In the numerical experiments, we use the universal evaluation metrics, such as the AP (average precision) @ IoU (Intersection over Union)=0.5 and mIoU (mean value of IoU) to evaluate the performance of precise localization. The experiment results show that our method outperforms the existing ones for precise object localization in AMMW images, where the improvement of the AP@0.5 is about 38% and that of the mIoU is about 27%.https://ieeexplore.ieee.org/document/9133393/AMMW imageconcealed object localizationsemantic segmentationdilated convolution |
| spellingShingle | Chongjian Wang Kehu Yang Xiaowei Sun Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation IEEE Access AMMW image concealed object localization semantic segmentation dilated convolution |
| title | Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation |
| title_full | Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation |
| title_fullStr | Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation |
| title_full_unstemmed | Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation |
| title_short | Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation |
| title_sort | precise localization of concealed objects in millimeter wave images via semantic segmentation |
| topic | AMMW image concealed object localization semantic segmentation dilated convolution |
| url | https://ieeexplore.ieee.org/document/9133393/ |
| work_keys_str_mv | AT chongjianwang preciselocalizationofconcealedobjectsinmillimeterwaveimagesviasemanticsegmentation AT kehuyang preciselocalizationofconcealedobjectsinmillimeterwaveimagesviasemanticsegmentation AT xiaoweisun preciselocalizationofconcealedobjectsinmillimeterwaveimagesviasemanticsegmentation |