Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences
Visual identification of objects using cameras requires precise detection, localization, and recognition of the objects in the field-of-view. The visual identification problem is very challenging when the objects look identical and features between distinct objects are indistinguishable, even with s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9718267/ |
| _version_ | 1818487812052221952 |
|---|---|
| author | Md Rashed Rahman T. V. Sethuraman Marco Gruteser Kristin J. Dana Shubham Jain Narayan B. Mandayam Ashwin Ashok |
| author_facet | Md Rashed Rahman T. V. Sethuraman Marco Gruteser Kristin J. Dana Shubham Jain Narayan B. Mandayam Ashwin Ashok |
| author_sort | Md Rashed Rahman |
| collection | DOAJ |
| description | Visual identification of objects using cameras requires precise detection, localization, and recognition of the objects in the field-of-view. The visual identification problem is very challenging when the objects look identical and features between distinct objects are indistinguishable, even with state-of-the-art computer vision techniques. The problem becomes significantly more challenging when the objects themselves do not carry rich geometric and photometric features, for example, in visual identification and tracking of light emitting diodes (LED) for visible light communication (VLC) applications. In this paper, we present a camera based visual identification solution where objects or regions of interest are tagged with an actively transmitting LED. Motivated by the concept of pilot symbols, typically used for synchronization and channel estimation in radio communication systems, the LED actively transmits unique pilot symbols which are detected by the camera across a series of image frames using our proposed spatio-temporal correlation based algorithm. We setup the visual identification as a problem of localization of the LED on the camera image, which involves identifying the (<italic>pixels</italic>) and the <italic>unique ID</italic> corresponding to the LED. In this paper, we present the algorithm and trace-based evaluation of the identification accuracy under real-world conditions including indoor, outdoor, static and mobile scenarios. In addition to micro-benchmarking the localization accuracy of our technique across different parameter configurations, we show that our technique outperforms comparative techniques, including, color based detection, support-vector machine based (SVM) machine learning, and you only look once (YOLO), which is a state-of-the-art convolutional neural network (CNN) deep learning based object identification tool. |
| first_indexed | 2024-12-10T16:42:50Z |
| format | Article |
| id | doaj.art-27dccb22117d4f44a61f9f31ceca87e1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T16:42:50Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-27dccb22117d4f44a61f9f31ceca87e12022-12-22T01:41:10ZengIEEEIEEE Access2169-35362022-01-0110243682438210.1109/ACCESS.2022.31537089718267Camera-Based Light Emitter Localization Using Correlation of Optical Pilot SequencesMd Rashed Rahman0https://orcid.org/0000-0002-2266-5092T. V. Sethuraman1Marco Gruteser2Kristin J. Dana3Shubham Jain4Narayan B. Mandayam5https://orcid.org/0000-0001-5744-0814Ashwin Ashok6https://orcid.org/0000-0002-6827-9154Department of Computer Science, Georgia State University, Atlanta, GA, USAIndian Institute of Technology (IIT) Madras, Chennai, IndiaGoogle, New York, NY, USAWINLAB/Department of ECE, Rutgers University, Piscataway, NJ, USADepartment of Computer Science, Stony Brook University, Stony Brook, NY, USAWINLAB/Department of ECE, Rutgers University, Piscataway, NJ, USADepartment of Computer Science, Georgia State University, Atlanta, GA, USAVisual identification of objects using cameras requires precise detection, localization, and recognition of the objects in the field-of-view. The visual identification problem is very challenging when the objects look identical and features between distinct objects are indistinguishable, even with state-of-the-art computer vision techniques. The problem becomes significantly more challenging when the objects themselves do not carry rich geometric and photometric features, for example, in visual identification and tracking of light emitting diodes (LED) for visible light communication (VLC) applications. In this paper, we present a camera based visual identification solution where objects or regions of interest are tagged with an actively transmitting LED. Motivated by the concept of pilot symbols, typically used for synchronization and channel estimation in radio communication systems, the LED actively transmits unique pilot symbols which are detected by the camera across a series of image frames using our proposed spatio-temporal correlation based algorithm. We setup the visual identification as a problem of localization of the LED on the camera image, which involves identifying the (<italic>pixels</italic>) and the <italic>unique ID</italic> corresponding to the LED. In this paper, we present the algorithm and trace-based evaluation of the identification accuracy under real-world conditions including indoor, outdoor, static and mobile scenarios. In addition to micro-benchmarking the localization accuracy of our technique across different parameter configurations, we show that our technique outperforms comparative techniques, including, color based detection, support-vector machine based (SVM) machine learning, and you only look once (YOLO), which is a state-of-the-art convolutional neural network (CNN) deep learning based object identification tool.https://ieeexplore.ieee.org/document/9718267/Visible light communication (VLC)object localization and trackingLED-camera communicationvisual tags in localizationidentical object tracking |
| spellingShingle | Md Rashed Rahman T. V. Sethuraman Marco Gruteser Kristin J. Dana Shubham Jain Narayan B. Mandayam Ashwin Ashok Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences IEEE Access Visible light communication (VLC) object localization and tracking LED-camera communication visual tags in localization identical object tracking |
| title | Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences |
| title_full | Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences |
| title_fullStr | Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences |
| title_full_unstemmed | Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences |
| title_short | Camera-Based Light Emitter Localization Using Correlation of Optical Pilot Sequences |
| title_sort | camera based light emitter localization using correlation of optical pilot sequences |
| topic | Visible light communication (VLC) object localization and tracking LED-camera communication visual tags in localization identical object tracking |
| url | https://ieeexplore.ieee.org/document/9718267/ |
| work_keys_str_mv | AT mdrashedrahman camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT tvsethuraman camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT marcogruteser camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT kristinjdana camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT shubhamjain camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT narayanbmandayam camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences AT ashwinashok camerabasedlightemitterlocalizationusingcorrelationofopticalpilotsequences |