Mark Bosley, Author at AI Robot Academy

Object Tracking is for Robots

Mark Bosley — Sun, 11 Jun 2023 03:07:24 +0000

Computer vision is a field of artificial intelligence that focuses on enabling computers and robots to understand the visual world.

Object tracking in Computer Vision is the task of automatically identifying objects in an image.

There are good tutorials on how to use Microsoft or Google’s apis to do object tracking on a picture or video frame. Most if not all use a picture taken by a photographer a few years in the past. A dated picture is not very useful for object tracking.

The following picture is from a Tutorial teaching how to do object tracking with Microsoft Cognitive Services.

In this example a kitchen appliance has been located at 730,66. Those coordinates are relative to the photographer who took the picture possibly years ago . Is that kitchen appliance there now? Probably not. Do you care?

However, If we use object tracking on a picture taken a few milliseconds previously on a robot we can use that data more effectively. The following picture frame was taken from a robot.

In real-time it records and applies object tracking frame by frame. In this example it identified a cat (on a picture card) while it was driving.

Perhaps you are not interested in cats. Maybe you want to train your robot to detect your neighbor’s dog. Or maybe you want to find Bigfoot. Object tracking is a wonderful technology. But where and how it is applied is very important. I am just saying old pictures are not interesting. Make it real-time.

The post Object Tracking is for Robots appeared first on AI Robot Academy.

Why Raspberry Pi 4 for a robot?

Mark Bosley — Thu, 08 Jun 2023 20:03:44 +0000

The Raspberry Pi 4 uses a Broadcom BCM2711, Quad core Cortex-A72 processor.

It includes a standard 40 pin GPIO header with which we can control a myriad of electronics components like range detectors ,motor controllers, and other electronic devices. The Raspberry Pi 4 has wi-fi support, connectors for cameras and speakers thus making it ideal for a plethora of projects. Due to its strong processor unit it is capable of handling AI abilities such as Computer Vision and Intents (Natural Language Understanding).

On the Raspberry Pi 4 website they list the price from $35. But due the supply chain issues it may be double or triple that even in 2023. But still amazingly cheap for a computer that is capable of running AI , motors, and other sensors at the same time.

The post Why Raspberry Pi 4 for a robot? appeared first on AI Robot Academy.

Learning AI with a robot

Mark Bosley — Wed, 07 Jun 2023 22:58:32 +0000

Most of us were introduced to Artificial Intelligence from the movies. We saw robots in movies like Chappie,Short Circuit, or Wall-e that could understand language, speak, and recognize what was around them. The good news is that these capabilities we saw in the movies are now finally realizable on robots. A Robot is an excellent platform for AI enthusiasts to learn from. For example there are many tutorials on how to demonstrate “Object Detection” from a picture. Like Microsoft’s article on object detection. They start off with a picture taken by a photographer. The picture was probably taken a few years previously. But detecting objects on a dated picture where the objects have probably moved or doesn’t exist in the current location is not particularly useful. But when one has a robot with a camera it changes the situation. Now when we handle object detection on a picture taken a few milliseconds previously then we are able to program the robot to react to what it sees. Perhaps we want our robot to speak to our pet when it comes into the room. Or maybe we want our robot to give out a shriek when the neighbor’s dog comes sniffing around on our lawn (you can imagine what might come next) . There are many other AI capabilities that we can add to our robot. We can place AI generated voices on our robot. Make our robot have a deep sounding voice. Or maybe we want it to sound like Dot Matrix in SpaceBalls. By the Way, There are many websites that can produce AI generated voices that are clones of a particular person. There are many wonderful and scary possibilities with this technology. Continuing on to what we can place on our robot. We can add Intents which would allow our robot to understand our verbal questions and commands( like Siri, Alexa, or other digital assistants). We can also add Sentiment Analysis to our robots so that the robot can determine if the emotional tone of our statements to the robot is positive, negative, or neutral. This would allow our robot to recognize if we are happy or sad. There are countless possibilties when we add AI to robots. What would you like to add?

Raspberry Pi 4 based Robot with mic, speaker, range detector, and camera

The post Learning AI with a robot appeared first on AI Robot Academy.