sample_embedding_folder2/0639528.txt

Ticket Name: TDA2EVM5777: Adaboost object detection training tool

Query Text:
Part Number: TDA2EVM5777 Other Parts Discussed in Thread: TDA2 Hi, everyone I saw Adaboost object detection training tool (Matlab based) is publicly available at https://github.com/tidsp/acf-jacinto And I download the Adaboost object detection training tool I have some questions 1. the training data's format should be .vbb .mp4 .seq ? Is .jpeg ( picture's format ) ok ? 2. What kind of file will be created if I use training tool to train the model ? (.xml or .bin or .....?) 3. If I want to use this file in TDA2 , where should I put ? Thanks Regards, Andy

Responses:
Hi Andy, I have forwarded your question to an expert for comment. Regards, Yordan

Hi Yordan, Is there any reply? Thanks! Regards, Andy

You need to provide both images and annotations. 1. The tool currently takes in .seq or .mp4 files for images. (It should be possible to modify the code to be able to specify a folder containing images instead of .seq or .mp4) 2. Annotation format supported is .vbb You can fiund lots of .seq files (with the corresponding .vbb annotations) here. http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/ An annotations/labelling code (matlab based) is also available in the above link. An enhanced version of the same labeling tool (supporting annotation of .mp4 files) is also provided here: https://github.com/tidsp/acf-jacinto/blob/master/vbb/vbbLabeler.m Note - you don't have to annotate all the frames. acf-jacinto is intelligent to understand which are the annotated frames and use only those for training. This feature is especially useful when dealing with .mp4 videos. After you do the training a .descriptor file will be written out. You can use this file in TDA2 VisionSDK Object Detection module. You can get more details in the documentation for the Object Detection module. Best regards,

HI Andy, Manu answered q1 and q2. Regarding your 3rd question, there is a utility to convert from the descriptor format to a a binary file which can be understand by OD module, The utility is unfortunately not packaged as part of object detection module, but let me see how can I get you access to the utility. Thanks, with Regards, Pramod