SCDS/FtcRobotControllerSDK
7
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated Blocks Sample TensorFlow Object Detection Op Mode (markdown)

FTC Engineering
2020-10-23 21:27:31 -04:00
parent a6b5ab5170
commit 469b1a64c5
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Blocks-Sample-TensorFlow-Object-Detection-Op-Mode.md

@ -41,9 +41,9 @@ In this example, the Op Mode activates the TensorFlow object detector before wai
<p align="center">[[/images/Blocks-Sample-TensorFlow-Object-Detection-Op-Mode/blocksTensorFlowActivate.png]]<br/>Activate TensorFlow.<p> <p align="center">[[/images/Blocks-Sample-TensorFlow-Object-Detection-Op-Mode/blocksTensorFlowActivate.png]]<br/>Activate TensorFlow.<p>
### Setting the Zoom Factor ### Setting the Zoom Factor
When TensorFlow receives an image from the robot's camera, the library downgrades the resolution of the image (presumably to achieve a higher detection rate). As a result, if a target is at a distance of around 24" (61cm) or more, the detection accuracy of the system tends to diminish. This degradation in detection accuracy can occur, even if your inference model is very accurate. When TensorFlow receives an image from the robot's camera, the library downgrades the resolution of the image (presumably to achieve a higher detection rate). As a result, if a target is at a distance of around 24" (61cm) or more, the detection accuracy of the system tends to diminish. This degradation can occur, even if you have a very accurate inference model.
You can specify a zoom factor in your op mode to offset the effect of this automatic scaling by the TensorFlow library. If you specify a zoom factor, the image will be cropped by this factor and this artificially magnified image will be passed to the TensorFlow library. The net result is that the robot should be able to detect and track an object at a significantly larger distance. You can specify a zoom factor in your op mode to offset the effect of this automatic scaling by the TensorFlow library. If you specify a zoom factor, the image will be cropped by this factor and this artificially magnified image will be passed to the TensorFlow library. The net result is that the robot is able to detect and track an object at a significantly larger distance. The webcams and built-in Android cameras that are typically used by FTC teans have high enough resolution to allow TensorFlow to "see" an artificially magnified target clearly.
<p align="center">[[/images/Blocks-Sample-TensorFlow-Object-Detection-Op-Mode/setZoom.png]]<br/>Set Zoom Factor.<p> <p align="center">[[/images/Blocks-Sample-TensorFlow-Object-Detection-Op-Mode/setZoom.png]]<br/>Set Zoom Factor.<p>