#cameras

AI is not a magical technology that simply happens to know a great deal about us. It is trained on a pipeline of people's information: video, audio, text. That's how it works. If you buy the device, it will monitor you.

Frigate is an open source NVR built around real-time AI object detection. All processing is performed locally on your own hardware, and your camera feeds never leave your home.

With their remote monitoring, motion detection, PTZ control, and data storing provisions, Network Video Recorders are a great way to turn a bunch of IP cameras into a full-fledged surveillance system. Better yet, the self-hosting landscape is chock-full of cool NVR solutions that not only let you manage your security footage, but also preserve your privacy and money while doing so. I’ve tinkered with a handful of these tools over the last couple of months, and while some may specialize in certain aspects, Frigate is ideal for building a DIY security camera system.

NVR with realtime local object detection for IP cameras

[Aaron’s] first video involves a simple teardown of the camera. The small plastic pill is a marvel of miniaturization. Through the hemispherical transparent lens, we can see a tiny camera and LEDs to provide light in the depths of the human body. Slicing the camera open reveals the hardware inside, however, like the miniature battery, the microcontroller, and the radio hardware that transmits signals outside the body. Unsurprisingly, it’s difficult to get into, since it’s heavily sealed to ensure the human body doesn’t accidentally digest the electronics inside.

Little Brother is burgeoning, too. More and more people are carrying cameras with them. Typically, these come in the form of mobile phones, but wearable cameras are growing in numbers and shrinking in size. Not too many years from now, lots of people will be wearing “heads-up” camera/display combos (such as Google Glass) that capture videos of pretty much everything they see. Unless we turn from the course we've set as a society, we'll soon arrive at a day when every square foot of every subway station—of just about every place, really—is being recorded at all times, and probably from multiple views. And all of these devices, capturing higher and higher resolution images plus audio, will be connected at high speeds to digital networks.

ZoneMinder is an integrated set of applications which provide a complete surveillance solution allowing capture, analysis, recording and monitoring of any CCTV or security cameras attached to a Linux based machine. It is designed to run on distributions which support the Video For Linux (V4L) interface and has been tested with video cameras attached to BTTV cards, various USB cameras and also supports most IP network cameras. A partial list is given in the Wiki and Support sections, please give feedback in the Forums if it works with yours. ZoneMinder also requires MySQL and PHP, and is enhanced by a webserver such as Apache.

ZoneMinder is an integrated set of applications which provide a complete surveillance solution allowing capture, analysis, recording and monitoring of any CCTV or security cameras attached to a Linux based machine. It is designed to run on distributions which support the Video For Linux (V4L) interface and has been tested with video cameras attached to BTTV cards, various USB cameras and also supports most IP network cameras. A partial list is given in the Wiki and Support sections, please give feedback in the Forums if it works with yours. ZoneMinder also requires MySQL and PHP, and is enhanced by a webserver such as Apache.

The Descriptive Camera works a lot like a regular camera—point it at subject and press the shutter button to capture the scene. However, instead of producing an image, this prototype outputs a text description of the scene. Modern digital cameras capture gobs of parsable metadata about photos such as the camera's settings, the location of the photo, the date, and time, but they don't output any information about the content of the photo. The Descriptive Camera only outputs the metadata about the content.

The Descriptive Camera works a lot like a regular camera—point it at subject and press the shutter button to capture the scene. However, instead of producing an image, this prototype outputs a text description of the scene. Modern digital cameras capture gobs of parsable metadata about photos such as the camera's settings, the location of the photo, the date, and time, but they don't output any information about the content of the photo. The Descriptive Camera only outputs the metadata about the content.

"what sets The Samsung TL9 ($280) apart from other cameras is MP3/PMP capability and two awesome empty/full analog gauges that track remaining battery life and memory capacity."

"These camera sunglasses certainly aren't x-ray specs, but they do capture 1.3 megapixel still images (at a resolution of 1280x1024)."