UPDATE!!!

We redesigned the GUI, and the program was optimized.

Have a look:

1、4 steps for pic recognition:

2、You can select bounding-box by yourself:

3、Video:

4、Load your own model:

Vehicle_Detection_Recognition

This is a Matlab lesson design for vehicle detection and recognition. Using cifar-10Net to training a RCNN, and finetune AlexNet to classify. Thanks to Cars Dataset : http://ai.stanford.edu/~jkrause/cars/car_dataset.html

Software

Matlab R2016b

Doadload

cars_meta.mat : http://pan.baidu.com/s/1mi6nvr6

cifar10NetRCNN.mat : (for Car position detection) http://pan.baidu.com/s/1geLa1V1

AlexNet_New.mat : (for Car type classify) http://pan.baidu.com/s/1bEzcYE

Code

You can use it to finish your task for single picture or video. Make sure your picture or video frame has 3 channels (colorful)

Citation

3D Object Representations for Fine-Grained CategorizationJonathan Krause, Michael Stark, Jia Deng, Li Fei-Fei4th IEEE Workshop on 3D Representation and Recognition, at ICCV 2013 (3dRR-13). Sydney, Australia. Dec. 8, 2013.

DataSet : http://ai.stanford.edu/~jkrause/cars/car_dataset.html

Effect

Actually, The running speed of the program is a bit of slow... Hope you can try Faster-Rcnn or yolo (you only look once).