The proposal mainly focuses on Convolutional Neural Network based object detection module to be integrated with the openDetection library. The library that will be used for this is caffe. The targets that will be accomplished are:1) Re-designing the library for CPU and GPU compilation modes. 2) Implement a way to invoke Caffe open source library from the OpenDetection module with a user-friendly code based way ( this will include a tinge of GUI support for instant access). 3) Implement open source guidance and codes for state-of-the art object localization problems(hypothesis generation) specifically based on selective-search and convolutional neural network (CNN) approaches. 4) Adding a ground-truth annotation tool to the module with a graphical-user-interface support. Implementing short, but effective modules like mixed-pooling, recurrent networks to the Convolutional Neural Networks Training dependent on the invoked caffe library. 5) Adding context based learning CNNs. 6) Adding user-interface to train and test CNN based classifiers and object detectors. 7)Adding documentation for the above

Organization

Student

Abhishek Kumar Annamraju

Mentors

  • Aditya
close

2016