Object detection algorithm on jetson TK1 for real-time

Autonomous Machines Jetson & Embedded Systems Jetson TK1
1

Hi,

I am novice in deep learning and currently working on object detection on Jetson TK1 with real-time video from a webcam. The two frameworks or applications I tired are

Darknet Yolo: Got 5-6 frames per second with Tiny-yolo configuration and tiny-yolo weights
Single shot multibox detector (works on caffe): got 5 fps

Has anyone used these or any other framework for object detection (classification and localization of objects in an image) for real-time video on the Jetsons? If yes, then what was the maximum frame rate achieved?

Are there better frameworks for the same?

Any help would be greatly appreciated.

Thanks,
BS

2

Hi BharatS,
On TK1, could you try with max performance Jetson/Performance - eLinux.org ?

We have samples of deep learning on tx1 but don’t have plan to make it to tk1. It would be good if you can try your case on tx1.

3

Hi DaneLLL,

Over clocking the system or using max performance did not improve the results. Yes, TX1 might help, but currently I am working only on TK1.

4

Hello, I saw your post and I am new to the jetson, I wanted to achieve the image/object detection using Yolo or SSD, can you please guide me through the process of achieving this? I know you said the max you achieved was 5-6 fps but this is something I’m really interested in and would like to at least get to that point :)

5

Hi,

Here are some relevant topics:

YOLO: (Yolo1 model can directly inference with TensorRT)
https://devtalk.nvidia.com/default/topic/990426/jetson-tx1/tensorrt-yolo-inference-error/

SSD: You need to enable their Caffe branch on TK1.
Please refer this: Install Caffe on NVIDIA Jetson TK1 LT4 21.2 - CUDA 6.5 · GitHub
Please remember to add TK1 GPU architecture into the Makefile.config
[url]https://devtalk.nvidia.com/default/topic/1020850/jetson-tk1/tk1-python-caffe-problems/post/5196767/#5196767[/url]

6

Hello, i am trying to get object detection working on jetson using darknet yolo. Can you please guide me step by step on how you achieved the 5-6 fps configuration working?

7

Hi,

We don’t have experience with darknet. Instead, we use TensorRT to inference YOLO model.
Check this topic: https://devtalk.nvidia.com/default/topic/990426/jetson-tx1/tensorrt-yolo-inference-error/