Apical’s Secure, Smart Home Motion Sensors Work LikeVideo Analytics without Video
SmartHome World 2015: Skirting bandwidth and privacy concerns, Apical’s smartmotion-sensor technology enables behavioral recognition without invasive videoanalytics. (Julie Jacobson / CE Pro)
Apical安全系统，智能家居移动传感器的工作方式与没有视频的视频分析相似
2015智能家居世界大会：踢脚板带宽和隐私问题。Apical的智能移动传感器技术无需介入视频分析就可以进行行为识别。
AtSmart Home World 2015, Apical discussed new sensor technology that enablesbehavioral analytics in an inexpensive motion sensor. (Video shown simply forcontext, but is not captured via Apical)
在2015智能家居世界大会上，Apical探讨了利用廉价的运动传感器进行行为分析的新传感器技术。（视频仅仅显示背景，但并不能通过Aprical捕捉）
By JulieJacobson, June 24, 2015
Julie Jacobson，2015年6月24日。
Traditionalsecurity sensors can tell you if motion is detected, and may go so far as todetermine if the mover is a person, a dog or branches swaying in the wind. Butthat’s pretty much it.
传统的安全传感器会告诉你是否检测到了移动，并且会进一步的确定移动的是人，狗或者在风中摇摆的树枝，差不多都是这样。
Formore data on the activity, and for richer integration with home automationsystems, you would step up to video analytics or wearables. Video analytics canhelp observers track objects, count people, recognize faces and even ascertainemotions. Wearables (as well as tags for objects) can more easily enablepersonal recognition and activity tracking.
为了获取更多活动的数据，并与家庭自动化系统进行更丰富的集成，你就需要赶紧分析视频或穿戴的设备。视频分析可以帮助观察者追踪目标，数人，识别面部以及确定表情。穿戴的设备（还有对象标签）可以很容易进行个人识别和活动追踪。
Bothof these solutions can be pricey and/or invasive. Furthermore, they can consumelarge amounts of data and require cloud-based processing.
A new sensor technology, Apical Resident Technology (ART) from London-basedApical Ltd.,enables much of the functionality of advanced video analytics andwearables, but without the bandwidth requirements and invasion of privacy.
这两种解决方案都很昂贵和/或者具有侵犯性。而且他们需要消耗大量的数据以及需要基于云技术的处理。一种新的传感器技术，来自于总部位于伦敦的Apical公司的Apical驻地技术（ART）保障了先进的视频分析以及穿戴设备的大部分功能，但是没有带宽的要求以及隐私的侵犯。
Thetechnology, which might be likened to a “very very good PIR” or “videoanalytics without the video,” looks at “pixel disruption” in light streams todecipher activity, according to Paul Strzelecki, a business consultant forApical Limited.
根据Apical有限公司的业务咨询Paul Strzelecki，这项技术很容易让人联想到“特别特别好的PIR传感器”或者“没有视频的视频分析技术”，它主要着眼于从光线流到破译活动的“像素扰乱”。
Infact, Apical’s legacy is in the video processing, with its technology embeddedin many a smart phone and surveillance camera. The new ART technology employsimage sensors like you might find in cameras, but extracts only the data, notthe images, thus reducing bandwidth requirements and dashing privacy concerns.
实际上，Apical的传统优势在于视频处理，并将此技术嵌入到很多智能手机以及监控摄像头中。新的ART技术使用了将会在相机中发现的图像传感器，但是只提取数据，而不是图像，这样就降低了带宽要求并减少了隐私问题。
Aswith video analytics, the ART technology is so accurate, says Strzelecki, thatit can “read” relationships between people as distant or intimate, for example.It can determine based on body language if a person might be threatening or inmedical distress.
Strzelecki说，与视频分析一样，ART技术非常准确，例如，它可以“阅读”出人之间的关系是亲密还是疏远。如果一个人处于威胁之中或医疗困扰中，它就可以基于人体语言加以鉴别。
Speakingat Smart Home World2015 inLondonthisweek, Apical CEO Michael Tusch explains that ART distills data into fourbuckets: trajectory, pose, gesture and identity. With that data, Apical’stechnology can 1) read people and behavior, 2) learn it and 3) generate eventsbased on the data.
在2015智能家居世界大会上的讲话中，Apical首席执行官Michael Tusch解释道：ART从四个方面提炼数据：踪迹，姿态，手势以及身份。有了这些数据后，Apical的技术可以：1）阅读人和行为，2）了解，3）基于数据生成事件。
Forexample, if an unknown person takes an unusual path across the front lawn, asystem might trigger the sprinklers to turn on.
Overtime, as a sensor network learns activities and behaviors in a household, a“system” becomes even more robust. It can potentially detect early stages ofAlzheimer’s disease based on very precise movements such as a person stoppingmid-way to the kitchen, pausing and reversing direction.
例如，如果一个陌生人在前面的草坪上不同寻常的走路，系统也许就会触发喷头开关。
随着时间的推移，当一个传感器网络掌握了家庭的活动和行为。“系统”就会变得更加强大。它可以基于一个人在前往厨房的途中停止，暂停以及折返等运动来监测早期阶段的阿尔茨海默病。
Thesensors can create a “behavioral footprint,” which Strzelecki calls BNA.
Ina more typical security application, the Apical technology can reduce falsealarms “almost to zero,” says Tusch, because it knows who should be wherewhen—even if an individual isn’t carrying a phone or wearing a magic bracelet.
Andall of this happens “entirely at the edge, at low power and low cost,” Tuschsays, who adds that raw data is captured continuously in real time at 60 fps.
(continuesafter video)
传感器可以创造一个“行为足迹”，这就是Strzelecki所谓的BNA。在更典型的安全性应用中，Apical技术可以将错误预警下降到“几乎为零”，Tusch说，因为它知道谁将在何时出现在何处，即使一个人并没有携带手机或者佩戴魔力手环。所有发生的这些“完全在边缘，能量更低以成本更低，”Tusch说。他还补充了粗略数据会以60fps被持续实时捕捉。（视频后继续）
Apical sensor technology
Again,this type of tracking is readily available today through video analytics or solong as the individual wears some kind of device and (typically) the cloud isinvolved. But Apical requires so little processing power and bandwidth thatinformation can be processed and stored locally at consumer-friendly prices.
“Noneof the information needs to go outside the house,” Strzelecki says. “If it’s inthe hardware, it can be processed on the fly.”
同样，这种类型的追踪可以通过视频数据分析或者只要个人佩戴某种设备并（典型的说）将云技术包含在内就可以实现。但是Apical需要极少的处理能量以及带宽，信息能够以用户可以接受的价格被处理和储存。“这些信息都无需走出房子”，Strzelecki说。“如果它存在于硬件中，那么在飞行的过程中也能处理”。
Imagine,for example, installing Apical-enabled sensors in the bathroom, where privacyis of utmost concern and individuals are apt to strip off wearables before ashower. An Apical-enabled sensor could nevertheless detect a fall or unusualactivity.
想象一下，例如，将Apical传感器安装在最关注隐私的浴室中，人们会在洗澡前会脱掉所有穿戴的设备，但Apical传感器仍然能够监测跌倒或不寻常的活动。
Strzeleckisays the Apical technology will be embedded into chipsets and ready fordeployment this year. Sensors with the technology should cost little more thantraditional PIRs, he says.
Strzelecki说，Apical技术将会嵌入到芯片组中并准备于今年部署开来。应用此项技术的传感器的成本应该比传统的PIR传感器要低，他说。
Tuschadds that Apical soon will announce a major partnership with aU.S.cameramanufacturer.
Tusch补充道，Apical将很快宣布与一个美国相机制造商的重要合作伙伴关系。
声明：本文为个人翻译最新商务类新闻文章，均有中英文对照，转载请与作者联系，尊重版权！
