Slashdot Mirror
Gunshot Tracking Cameras to be Deployed in LA
apok04 writes "Get out your tinfoil hats (and ski masks). A USC engineer uses his expertise with nerve cells to create a surveillance system that can recognize the sound of a nearby gunshot - and identify the shooter. In a unique pilot program, L.A. and Chicago will deploy test units in high-crime areas. The creator emphasizes that the system cannot recognize voices or words, but his previous research into speech recognition systems suggests otherwise."
The system can then locate, precisely, where the shot was fired, turn a camera to center the shooter in the camera viewfinder and make a 911 call to a central police station.
If the shooter is still there, she deserves to be caught.
According to the article, this device is listening for the entire sound pattern of the gunshot, not just the initial explosion, which makes it much less likely to mistake other loud noises for shooting.
So it may be difficult to fool it unless you can also simulate the whole shooting sequence (think of Matrix's bullet time).
I guess FPS game developers can use one of these to create realistic gunshot sounds.
Rock that crushes, Paper & Scissors that don't matter.
If the surveilance system will determine who fired before it ceases to function due to gunshot damage.
In unrelated news, sources report that knive sales have skyrocketed in recent days. No plausible explanation could be found.
Uh, no, it doesn't. The fact that the guy has worked on different types of signal processing doesn't "suggest" that he builds those capacities into every project he touches.
What I'm listening to now on Pandora...
During the initial studies the camera was placed in front of a TV with Star Wars on it. The sophisticated equipment could still not tell who shot first between Greedo or Han.
In a unique pilot program, L.A. and Chicago will deploy test units in high-crime areas.
Hmmm... Let me guess, the south side of Chicago and Compton?
Rather than looking for pro-active solutions to lowering crime in lower-income neighborhoods, like good education systems, quality health-care, living wages, etc. we continue to see crazy-ass reactive schemes like the above camera system that don't do anything to solve the real problems. In the meantime, as these useless systems become the norm, our society moves closer and closer to the ultimate police heaven, where everyone is monitored every second of every day. When's it gonna end?
Hey, golly-gee-whiz, it sure is a neat technology, Wally.
But like most things of that sort, no one's actually thought about how it actually makes things better, or how it can make things worse. So you catch a few people shooting guns, so what? They end up in jail, their families get torn apart, their chances of actually becoming a productive part of society diminish and they end up back on the street shooting a gun again, which is caught on camera, etc. etc. etc. Wow, crime sure is decreasing now.
It's nice to talk about being tough on crime, but oftentimes what's really needed is not the cracking of a whip, or the monitoring of a camera, but rather a signature on a diploma, or on a paycheck. If you start suspecting everyone as a criminal, then they start seeing themselves as criminals and it becomes a self-fulfilling prophecy. If you first look at people as raw material that can be shaped and molded into something productive, well, you see what I'm getting at.
I'm getting sick of reading about high-tech crime monitoring systems, but it's appearing to be inevitable that we will live with them in our daily lives now and in the near future, so let me practice my indoctrination recitation:
"I for one, welcome our all-seeing camera overlords."
+1 Insightful, -1 Troll. What can I say, I'm an Insightful Troll.
A buddy of mine and I did this in a physics lab. We used an array of 5 condenser mics wired into a PC running LabView, wired out to a laser pointer mounted on some toy motors.
Someone would clap 15-30 feet away, and the computer pointed the laser pointer at their hands. We got the position within a foot or so, even in a echoing cinder block room.
Insights:
- You need at least 4 mics to get an object's position. (There are 4 degrees of freedom, x, y, z, and time) If you only need the angle, then you need 3 (for time, theta, and phi).
- There are some places to shoot where due to the symmetries, it would be hard to compute a position. If the mics are arranged in a plane, then one problem area is straight out from the mic, normal to the plane.
- Another project group in my class developed a computer-controlled ball bearing cannon. I wish we had time to link the projects.
- Thermal variation in the air can disrupt your results.
- If you used well-tuned directional mics, you might be better off. Rather than compute the location based on the path-length of the sound to each mic, you could then find out the incident angle of the sound on each mic, based upon how much the sound level is reduced.