Joint Object Detection and Depth Estimation in Multiplexed Image
This paper presents an object detection method that can simultaneously estimate the positions and depth of the objects from multiplexed images. Multiplexed image is produced by a new type of imaging device that collects the light from different fields of view using a single image sensor, which is or...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8805052/ |
| _version_ | 1818416092400320512 |
|---|---|
| author | Changxin Zhou Yazhou Liu Quansen Sun Pongsak Lasang |
| author_facet | Changxin Zhou Yazhou Liu Quansen Sun Pongsak Lasang |
| author_sort | Changxin Zhou |
| collection | DOAJ |
| description | This paper presents an object detection method that can simultaneously estimate the positions and depth of the objects from multiplexed images. Multiplexed image is produced by a new type of imaging device that collects the light from different fields of view using a single image sensor, which is originally designed for stereo, 3D reconstruction and broad view generation using computational imaging. Intuitively, multiplexed image is a blended result of the images of multiple views and both of the appearance and disparities of objects are encoded in a single image implicitly, which provides the possibility for reliable object detection and depth/disparity estimation. Motivated by the recent success of CNN based detector, a multi-anchor detector method is proposed, which detects all the views of the same object as a clique and uses the disparity of different views to estimate the depth of the object. The proposed method is interesting in the following aspects: firstly, both locations and depth of the objects can be simultaneously estimated from a single multiplexed image; secondly, there is almost no computation load increase comparing with the popular object detectors; thirdly, even in the blended multiplexed images, the detection and depth estimation results are very competitive. There is no public multiplexed image dataset yet, therefore the evaluation is based on the simulated multiplexed image using the stereo images from KITTI, and very encouraging results have been obtained. |
| first_indexed | 2024-12-14T11:45:23Z |
| format | Article |
| id | doaj.art-e39ae12efe24458ab57b9a12ec03a8ac |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T11:45:23Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e39ae12efe24458ab57b9a12ec03a8ac2022-12-21T23:02:38ZengIEEEIEEE Access2169-35362019-01-01712310712311510.1109/ACCESS.2019.29361268805052Joint Object Detection and Depth Estimation in Multiplexed ImageChangxin Zhou0Yazhou Liu1https://orcid.org/0000-0002-0631-2385Quansen Sun2Pongsak Lasang3School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaCore Technology Group, Panasonic R&D Center Singapore, SingaporeThis paper presents an object detection method that can simultaneously estimate the positions and depth of the objects from multiplexed images. Multiplexed image is produced by a new type of imaging device that collects the light from different fields of view using a single image sensor, which is originally designed for stereo, 3D reconstruction and broad view generation using computational imaging. Intuitively, multiplexed image is a blended result of the images of multiple views and both of the appearance and disparities of objects are encoded in a single image implicitly, which provides the possibility for reliable object detection and depth/disparity estimation. Motivated by the recent success of CNN based detector, a multi-anchor detector method is proposed, which detects all the views of the same object as a clique and uses the disparity of different views to estimate the depth of the object. The proposed method is interesting in the following aspects: firstly, both locations and depth of the objects can be simultaneously estimated from a single multiplexed image; secondly, there is almost no computation load increase comparing with the popular object detectors; thirdly, even in the blended multiplexed images, the detection and depth estimation results are very competitive. There is no public multiplexed image dataset yet, therefore the evaluation is based on the simulated multiplexed image using the stereo images from KITTI, and very encouraging results have been obtained.https://ieeexplore.ieee.org/document/8805052/Object detectiondepth estimationmultiplexed image |
| spellingShingle | Changxin Zhou Yazhou Liu Quansen Sun Pongsak Lasang Joint Object Detection and Depth Estimation in Multiplexed Image IEEE Access Object detection depth estimation multiplexed image |
| title | Joint Object Detection and Depth Estimation in Multiplexed Image |
| title_full | Joint Object Detection and Depth Estimation in Multiplexed Image |
| title_fullStr | Joint Object Detection and Depth Estimation in Multiplexed Image |
| title_full_unstemmed | Joint Object Detection and Depth Estimation in Multiplexed Image |
| title_short | Joint Object Detection and Depth Estimation in Multiplexed Image |
| title_sort | joint object detection and depth estimation in multiplexed image |
| topic | Object detection depth estimation multiplexed image |
| url | https://ieeexplore.ieee.org/document/8805052/ |
| work_keys_str_mv | AT changxinzhou jointobjectdetectionanddepthestimationinmultiplexedimage AT yazhouliu jointobjectdetectionanddepthestimationinmultiplexedimage AT quansensun jointobjectdetectionanddepthestimationinmultiplexedimage AT pongsaklasang jointobjectdetectionanddepthestimationinmultiplexedimage |