Omnidirectional coverage for device free passive human detection
Download as DOCX, PDF0 likes225 views
The document discusses a novel approach to omnidirectional passive human detection using existing Wi-Fi infrastructure, harnessing multipath effects to enhance coverage. It proposes a fingerprinting scheme and a threshold-based scheme, achieving an average false positive rate of 8% and a false negative rate of 7% for detecting human presence. This method aims to improve passive human detection capabilities, essential for smart spaces and human-computer interaction.
Omnidirectional coverage for device free passive human detection
- 1. ECRUITMENT SOLUTIONS (0)9751442511, 9750610101 #1, Ist Cross, Ist Main Road, Elango Nagar,Pondicherry-605 011. tech@ecruitments.com www.ecruitments.com Omnidirectional Coverage for Device-Free Passive Human Detection ABSTRACT: Device-free Passive (DfP) human detection acts as a key enabler for emerging location-based services such as smart space, human-computer interaction, and asset security. A primary concern in devising scenario- tailored detecting systems is coverage of their monitoring units. While disk- like coverage facilitates topology control, simplifies deployment analysis, and is crucial for proximity-based applications, conventional monitoring units demonstrate directional coverage due to the underlying transmitter- receiver link architecture. To achieve omnidirectional coverage under such link-centric architecture, we propose the concept of omnidirectional passive human detection. The rationale is to exploit the rich multipath effect to blur the directional coverage. We harness PHY layer features to robustly capture the fine-grained multipath characteristics and virtually tune the shape of the coverage of the monitoring unit, which is previously prohibited with mere MAC layer RSSI. We design a fingerprinting scheme and a threshold-based scheme with off-the-shelf Wi-Fi infrastructure and evaluate both schemes in typical clustered indoor scenarios. Experimental results demonstrate an average false positive of 8 percent and an average false negative of 7 percent for fingerprinting in detecting human presence in 4 directions. And both average false positive and false negative remain around 10 percent even with threshold-based methods.
- 2. ECRUITMENT SOLUTIONS (0)9751442511, 9750610101 #1, Ist Cross, Ist Main Road, Elango Nagar,Pondicherry-605 011. tech@ecruitments.com www.ecruitments.com EXISTING SYSTEM: We propose the concept of omnidirectional passive human detection. The rationale is to exploit the rich multipath effect to blur the directional coverage. We harness PHY layer features to robustly capture the fine- grained multipath characteristics and virtually tune the shape of the coverage of the monitoring unit, which is previously prohibited with mere MAC layer RSSI. We design a fingerprinting scheme and a threshold- based scheme with off-the-shelf Wi-Fi infrastructure and evaluate both schemes in typical clustered indoor scenarios. Experimental results demonstrate an average false positive of 8 percent and an average false negative of 7 percent for fingerprinting in detecting human presence in 4 directions. And both average false positive and false negative remain around 10 percent even with threshold-based methods. Our scheme is implemented on existing WLAN infrastructure with off-the-shelf Intel 5300 Network Interface Card (NIC), requiring no extra hardware supports. We validate our scheme in typical indoor scenarios, considering both stationary and mobile user detection. PROPOSED SYSTEM: The coverage shape of the proposed scheme is still not perfectly omnidirectional. Finer-grained and more effective features extracted from
- 3. ECRUITMENT SOLUTIONS (0)9751442511, 9750610101 #1, Ist Cross, Ist Main Road, Elango Nagar,Pondicherry-605 011. tech@ecruitments.com www.ecruitments.com channel responses might ultimately contribute to a perfect disk-like coverage. We extract distinctive features from the small-scale spectral structures of multipath components that are sensitive to nearby human locomotion and resistant to irrelevant background dynamics. Leveraging the histograms of CSI as signatures for different directions, we propose Omni-PHD, an omnidirectional passive human detection scheme and prototype it with mere commercial Wi-Fi infrastructure. CONCLUSION: We demonstrate that PHY layer information unfolds new possibilities for passive human detection. Exploiting rich multipath effect indoors, we blur the link centric property of traditional monitoring units and explore omnidirectional cell coverage. We extract distinctive features from the small-scale spectral structures of multipath components that are sensitive to nearby human locomotion and resistant to irrelevant background dynamics. Leveraging the histograms of CSI as signatures for different directions, we propose Omni-PHD, an omnidirectional passive human detection scheme and prototype it with mere commercial Wi-Fi infrastructure. Experiments considering the richness of multipath, background dynamics and mobility demonstrated an average false positive of 8 percent and false negative of 7 percent in detecting human presence in 4 directions for fingerprinting, and both average false positive and false negative of around 10 percent with a single threshold based method. We envision this work as an early step towards passive human detection with flexible coverage, which acts as a crucial concern in human-centric computing.
- 4. ECRUITMENT SOLUTIONS (0)9751442511, 9750610101 #1, Ist Cross, Ist Main Road, Elango Nagar,Pondicherry-605 011. tech@ecruitments.com www.ecruitments.com