Phase 9 - Project Demo Test Results
Phase 9 - Project Demo Test Results
Acceptance Tests - AT |week 15|
Acceptance Tests - AT |week 15|
Embedded Files
The whole OCS System is composed of mechanisms that implement image acquisition, classification, sorting, and rejection. The image is captured using the web camera and pre-processed to go through our Convolutional Neural Network, titled OCS. The classification process follows. It determines if the object placed on our platform is one of the three objects it was trained for. In the case that the OCS network has 99% confidence or greater, the robotic arm will place the item in its allocated container. In the case that the item isn’t one of our three objects, a lever rejects the item off the platform to set space for another object to be classified.
OCS Systems Architecture is composed of image acquisition, deep learning, transfer learning, classification, rejection, and sorting
OCS team has executed successive tests to validate the project objectives.
- Classify objects with over 99% accuracy using deep learning techniques.
- Establish communication between Matlab and Arduino.
- Pick and place objects into their designated locations.
- Reject unknown objects.
OCS final Transfer Learning is performed using AlexNet on a single GPU and we have obtained a 100% learning validation accuracy and above 99% classification accuracy.
Transfer Learning Result. 100% learning validation accuracy
Classification on three known objects. Above 99% classification accuracy
OSC System Requirements - Acceptance Test Status and Results
Our system satisfies all our system requirements shown on the following spreadsheet
Our system satisfies all our system requirements shown on the following spreadsheet
AT Type Descriptions
System Requirement “OCS 02”
System Requirement “OCS 02” is incorporated, tested, & passed.
System Requirement “OCS 03”
System Requirement “OCS 03” is incorporated, tested, & passed. RGB LED light is mounted on the object positioning platform and it provides a visual indication.
System Requirement “OCS 06”
System Requirement “OCS 03” tested and passed. All units under test are classified above 99% accuracy.
EE400D-Test_5.mp4OCS classification, rejection, and sorting Test
Google Sites
Report abuse