YOLOv2 Real-Time Object Detection on KITTI

preview_player
Показать описание
This is a test of YOLOv2 on KITTI. YOLOv2 is the state of the art object detector. And it is also amazingly fast and easy to use.
* I am not the author of YOLO. I just use it to train on KITTI.

Input Image Size = 1238 x 374 (KITTI data_tracking_image_2/training/image_02/0019)
Numbers of Frames = 1057
Network Input Size = 1280 x 384 (set close to input image size)
Measured Speed = 24.1 fps (including all processing time)
Hardware = i7-7700K / 32G DDR4 / GTX1070 / SSD
OS = Ubuntu 16.04 64bit
  1. Cory Lee
Рекомендации по теме
YOLOv2 Real-Time Object 0:00:52

YOLOv2 Real-Time Object Detection on KITTI

#YOLOv2 : Real-Time 0:02:24

#YOLOv2 : Real-Time Object Detection In Turkey Traffic

Real Time Object 0:02:01

Real Time Object Detection Test using YOLO v2 on NVIDIA Jetson TX2

Real-time object detection 0:00:37

Real-time object detection using TensorFlow (Yolo Algorithm v2)

Real time object 0:01:01

Real time object detection YOLOv2

YOLOv2 Object Detection 0:00:20

YOLOv2 Object Detection Video

Applied machine learning 0:00:46

Applied machine learning example - Real time object detection with YOLO v2

Bangalore night traffic 0:00:35

Bangalore night traffic real time object detection by deep learning by YOLO , OpenCV, TensorFlow

YOLOV2 Object Detection 0:04:58

YOLOV2 Object Detection

Real Time Object 0:05:10

Real Time Object Detection YOLOv2 using Pytorch

Yolo v2 image 0:00:07

Yolo v2 image detection

Image Detection with 0:12:33

Image Detection with YOLO v2 (pt 4) Real Time YOLO with Webcam

YOLOv2 - Object 0:03:45

YOLOv2 - Object Detection

Real-time object detection 0:00:05

Real-time object detection in Flutter with camera and tflite plugin

Real-time Object Detection 0:00:57

Real-time Object Detection demo with binary weight YOLO v2 on FPGA

Real-time Jaywalker Monitoring 0:00:31

Real-time Jaywalker Monitoring Platform using YOLOv2

Real-Time Object Detection 0:04:25

Real-Time Object Detection with YOLO v2 Using GPU Coder

Object Detection in 0:03:14

Object Detection in a Video Using YOLO V2

Object Detection with 0:00:13

Object Detection with YOLO V2

Object-detection using YOLOv2 0:00:21

Object-detection using YOLOv2 in crowded Sarojni market

Object Detection with 0:00:15

Object Detection with YOLOv2

yolov2 0:00:51

yolov2

Object detection with 0:00:29

Object detection with YOLOv2-tiny

Applied Machine Learning 0:02:26

Applied Machine Learning example - Real time object detection with YOLO v2

Комментарии
Автор

can i get the tutorial code for the same as i am new to python and image classification?

atulshukla
Автор

wow it's great
how to get code?
and what is the computer specifications?

김대한-zu
Автор

My laptop have graphics processor GeForce 820M, is it possible 😰😰

sahiltamboli
Автор

I am trying to train yolov2 on kitti tracking dataset too using darkflow (darknet for tensorflow). So far i tried the 416*416 resolution; it didn't produce good result. I wonder whether should i tried 1280 * 384 resolution like yours.

YBStark
Автор

Dear Cory:
1. Have u modify the grid size 7 to bigger value, to get the better performance on detect smaller object?
Or u get this result without modify the grid size?
2. Have u change the setting of the anchors in the cfg file?

Becuz now I will train for my own dataset(resolution: 1920*1080), I wonder how should I modify the settings I mentioned before.

Thanks for ur reply!

ctyang
join shbcf.ru