{"id":24703,"date":"2018-06-25T13:57:37","date_gmt":"2018-06-25T17:57:37","guid":{"rendered":"https:\/\/www.tun.com\/blog\/?p=24703"},"modified":"2022-03-16T10:50:08","modified_gmt":"2022-03-16T14:50:08","slug":"surveillance-cameras-talk-to-public-via-smartphones","status":"publish","type":"post","link":"https:\/\/www.tun.com\/blog\/surveillance-cameras-talk-to-public-via-smartphones\/","title":{"rendered":"Surveillance Cameras \u2018Talk\u2019 to the Public via Smartphones"},"content":{"rendered":"

Researchers at Purdue University have developed a <\/span>new technology<\/span><\/a> that enables public surveillance cameras to communicate with people. <\/span><\/p>\n

The system, which they have named PHADE, can send real-time, personalized messages to smartphones based on users\u2019 behavior, all without compromising the privacy of the individual.<\/span><\/p>\n

This private human addressing process can be used for various purposes in locations as diverse as museums, supermarkets, and on the streets, according to the researchers.<\/span><\/p>\n

\u201cSurveillance cameras are widely deployed,\u201d said <\/span>He Wang<\/span><\/a>, an assistant professor in the <\/span>Purdue Department of Computer Science<\/span><\/a>, who created the technology along with <\/span>Siyuan Cao<\/span><\/a>, the lead doctoral student for the project. \u201cHuman or AI systems can retrieve numerous information from the video feeds of these cameras. <\/span><\/p>\n

\u201cVideo analytics is a killer application of edge computing. Beyond just analyzing video streams, ideally, the cameras should be able to send customized messages to a target in its view \u2013 for instance, coupons based on the target\u2019s behavior, a security alert to a pedestrian who is too focused on the phone to be aware of approaching vehicles, etc.\u201d <\/span><\/p>\n

\u201cUnfortunately,\u201d he continued, \u201cthere is no way to do this today, because the IP address or numbers of the target\u2019s phone are unknown to the camera.\u201d<\/span><\/p>\n

PHADE is specifically designed to work around this problem. <\/span><\/p>\n

The <\/span>paper<\/span><\/a> describing the research will be published in the June 2018 issue of <\/span>Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)<\/span><\/a>, and will be presented at an international joint conference on pervasive and ubiquitous computing (<\/span>UBICOMP 2018<\/span><\/a>), to be held Oct. 8-11 in Singapore.<\/span><\/p>\n

How does PHADE work?<\/b><\/h2>\n

Traditional data transmission protocols require a destination\u2019s IP or MAC address to send such messages. <\/span><\/p>\n

The PHADE system, however, doesn\u2019t require an IP address, MAC address, phone number, or face recognition to identify a person and send it a targeted message. <\/span><\/p>\n

Rather, PHADE uses motion patterns as the address code for messages, allowing it to send the message without such information, and without violating the privacy of the recipient.<\/span><\/p>\n

PHADE receives video streams from surveillance cameras via a server. When a person enters the camera\u2019s view, the camera detects and tracks the person\u2019s movement. <\/span><\/p>\n

The camera analyzes the person\u2019s mov<\/span>ement and prepares a \u201cpacket\u201d containing a message specifically designed for the person based on his or her action, as well as an address code identifying the person\u2019s location. <\/span><\/p>\n

The camera then broadcasts this packet, allowing it to be picked up by the smartphone at the person\u2019s location.<\/span> When the packet is received by a smartphone, the smartphone compares the address code with its sensor data and uses this information to decide whether or not to accept it.<\/span><\/p>\n

Key features of this process ensure the privacy of the message recipients\u2019 information.<\/span><\/p>\n

\u201cThe system makes users\u2019 smartphones locally decide what messages to accept,\u201d said Cao. \u201cIt means that the clients don\u2019t need to upload any sensor data to the server.<\/span><\/p>\n

\u201cPHADE also uses PCA (principal component analysis) to transform motion features into lower-dimensional address codes. This blurs details in the raw motion data and prevents targets\u2019 walking history from being recovered.\u201d<\/span><\/p>\n

In experiments testing the effectiveness of this technology, PHADE was able to locate and send messages to recipients with a matching correctness rate of around 90 percent.<\/span><\/p>\n