Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics
With the growing prevalence of large-scale intelligent surveillance camera systems, the burden on real-time video analytics pipelines has significantly increased due to continuous video transmission from numerous cameras. To mitigate this strain, recent approaches focus on filtering irrelevant video...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/3/701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850199936932511744 |
|---|---|
| author | Lawrence Lubwama Jungik Jang Jisung Pyo Joon Yoo Jaehyuk Choi |
| author_facet | Lawrence Lubwama Jungik Jang Jisung Pyo Joon Yoo Jaehyuk Choi |
| author_sort | Lawrence Lubwama |
| collection | DOAJ |
| description | With the growing prevalence of large-scale intelligent surveillance camera systems, the burden on real-time video analytics pipelines has significantly increased due to continuous video transmission from numerous cameras. To mitigate this strain, recent approaches focus on filtering irrelevant video frames early in the pipeline, at the camera or edge device level. In this paper, we propose Wi-Filter, an innovative filtering method that leverages Wi-Fi signals from wireless edge devices, such as Wi-Fi-enabled cameras, to optimize filtering decisions dynamically. Wi-Filter utilizes channel state information (CSI) readily available from these wireless cameras to detect human motion within the field of view, adjusting the filtering threshold accordingly. The motion-sensing models in Wi-Filter (Wi-Fi assisted Filter) are trained using a self-supervised approach, where CSI data are automatically annotated via synchronized camera feeds. We demonstrate the effectiveness of Wi-Filter through real-world experiments and prototype implementation. Wi-Filter achieves motion detection accuracy exceeding 97.2% and reduces false positive rates by up to 60% while maintaining a high detection rate, even in challenging environments, showing its potential to enhance the efficiency of video analytics pipelines. |
| format | Article |
| id | doaj-art-e2715d2d24c84443887f9638261d8404 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-e2715d2d24c84443887f9638261d84042025-08-20T02:12:29ZengMDPI AGSensors1424-82202025-01-0125370110.3390/s25030701Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video AnalyticsLawrence Lubwama0Jungik Jang1Jisung Pyo2Joon Yoo3Jaehyuk Choi4School of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-gu, Seongnam-si 13120, Republic of KoreaSchool of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-gu, Seongnam-si 13120, Republic of KoreaSchool of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-gu, Seongnam-si 13120, Republic of KoreaSchool of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-gu, Seongnam-si 13120, Republic of KoreaSchool of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-gu, Seongnam-si 13120, Republic of KoreaWith the growing prevalence of large-scale intelligent surveillance camera systems, the burden on real-time video analytics pipelines has significantly increased due to continuous video transmission from numerous cameras. To mitigate this strain, recent approaches focus on filtering irrelevant video frames early in the pipeline, at the camera or edge device level. In this paper, we propose Wi-Filter, an innovative filtering method that leverages Wi-Fi signals from wireless edge devices, such as Wi-Fi-enabled cameras, to optimize filtering decisions dynamically. Wi-Filter utilizes channel state information (CSI) readily available from these wireless cameras to detect human motion within the field of view, adjusting the filtering threshold accordingly. The motion-sensing models in Wi-Filter (Wi-Fi assisted Filter) are trained using a self-supervised approach, where CSI data are automatically annotated via synchronized camera feeds. We demonstrate the effectiveness of Wi-Filter through real-world experiments and prototype implementation. Wi-Filter achieves motion detection accuracy exceeding 97.2% and reduces false positive rates by up to 60% while maintaining a high detection rate, even in challenging environments, showing its potential to enhance the efficiency of video analytics pipelines.https://www.mdpi.com/1424-8220/25/3/701Wi-Fi sensingchannel state informationvideo frame filtering1D CNNedge computing |
| spellingShingle | Lawrence Lubwama Jungik Jang Jisung Pyo Joon Yoo Jaehyuk Choi Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics Sensors Wi-Fi sensing channel state information video frame filtering 1D CNN edge computing |
| title | Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics |
| title_full | Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics |
| title_fullStr | Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics |
| title_full_unstemmed | Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics |
| title_short | Wi-Filter: WiFi-Assisted Frame Filtering on the Edge for Scalable and Resource-Efficient Video Analytics |
| title_sort | wi filter wifi assisted frame filtering on the edge for scalable and resource efficient video analytics |
| topic | Wi-Fi sensing channel state information video frame filtering 1D CNN edge computing |
| url | https://www.mdpi.com/1424-8220/25/3/701 |
| work_keys_str_mv | AT lawrencelubwama wifilterwifiassistedframefilteringontheedgeforscalableandresourceefficientvideoanalytics AT jungikjang wifilterwifiassistedframefilteringontheedgeforscalableandresourceefficientvideoanalytics AT jisungpyo wifilterwifiassistedframefilteringontheedgeforscalableandresourceefficientvideoanalytics AT joonyoo wifilterwifiassistedframefilteringontheedgeforscalableandresourceefficientvideoanalytics AT jaehyukchoi wifilterwifiassistedframefilteringontheedgeforscalableandresourceefficientvideoanalytics |