Navigation

    蓝鲸ROS机器人论坛

    • Register
    • Login
    • Search
    • Categories
    • Tags
    • Popular
    ROS交流群
    ROS Group
    产品服务
    Product Service
    开源代码库
    Github
    官网
    Official website
    技术交流
    Technological exchanges
    激光雷达
    LIDAR
    ROS教程
    ROS Tourials
    深度学习
    Deep Learning
    机器视觉
    Computer Vision

    在小强上使用body_pose进行人体识别

    技术交流
    深度学习 机器视觉
    6
    20
    5095
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • weijiz
      weijiz @robot0612 last edited by

      @robot0612 是不是模型没有下载完整,重新执行下载模型的指令试试

      1 Reply Last reply Reply Quote 0
      • robot0612
        robot0612 last edited by robot0612

        模型重新下载了。运行还是出现这个问题:cf613e6b-fe38-4e6b-827b-cabd6695ba4c-image.png

        weijiz 2 Replies Last reply Reply Quote 0
        • weijiz
          weijiz @robot0612 last edited by

          @robot0612 感觉你的python环境可能有问题,错误的代码语法是python3的,但是却出现在python2.7的路径里面

          1 Reply Last reply Reply Quote 0
          • weijiz
            weijiz @robot0612 last edited by

            @robot0612 里面的一个依赖库新版本不支持python2.7了。需要下载旧版本

            pip install munkres==1.0.12
            
            1 Reply Last reply Reply Quote 0
            • lm213
              lm213 last edited by

              这个姿态识别包用的什么算法啊?大概实现的原理能说一下吗?

              weijiz 1 Reply Last reply Reply Quote 0
              • weijiz
                weijiz @lm213 last edited by

                @lm213 这个包是由这里改出来的,说明里面有算法的论文。具体的我也没看,不太清楚

                1 Reply Last reply Reply Quote 0
                • lm213
                  lm213 last edited by

                  This post is deleted!
                  1 Reply Last reply Reply Quote 0
                  • lm213
                    lm213 last edited by lm213

                    This post is deleted!
                    1 Reply Last reply Reply Quote 0
                    • lm213
                      lm213 last edited by

                      This post is deleted!
                      1 Reply Last reply Reply Quote 0
                      • lm213
                        lm213 last edited by

                        This post is deleted!
                        1 Reply Last reply Reply Quote 0
                        • moist
                          moist last edited by

                          执行单人姿态识别成功,没有报错。
                          执行多人姿态识别时候报错如下
                          Traceback (most recent call last):
                          File “demo/demo_multiperson.py”, line 17, in
                          from multiperson.detections import extract_detections
                          File “demo/…/multiperson/detections.py”, line 10, in
                          from nms_grid import nms_grid
                          ImportError: No module named nms_grid

                          ROS执行报错如下,好像是同名节点的问题:
                          [camera_node-5] process has died [pid 31196, exit code 1, cmd /home/xiaoqiang/Documents/ros/devel/lib/usb_cam/usb_cam_node __name:=camera_node __log:=/home/xiaoqiang/.ros/log/b7b359c8-2222-11eb-ae28-cfd9b2d8c1b5/camera_node-5.log].
                          log file: /home/xiaoqiang/.ros/log/b7b359c8-2222-11eb-ae28-cfd9b2d8c1b5/camera_node-5*.log
                          shutdown request: new node registered with same name
                          有懂的朋友麻烦解释一下,感谢。

                          weijiz 1 Reply Last reply Reply Quote -1
                          • weijiz
                            weijiz @moist last edited by

                            @moist 可能你的模型没有下载完整

                            marcos452 1 Reply Last reply Reply Quote 0
                            • marcos452
                              marcos452 last edited by

                              This post is deleted!
                              1 Reply Last reply Reply Quote 0
                              • marcos452
                                marcos452 @weijiz last edited by marcos452

                                @weijiz 您好,我roslaunch body_pose body_pose_test.launch后
                                出现如下情况
                                [WARN] [1605520393.882227]: Cannot get image from ~image
                                [WARN] [1605520394.884241]: Cannot get image from ~image
                                但是我点击鼠标右键会出现以下命令
                                [ INFO] [1605520396.100524512]: Saved image frame0004.jpg
                                然后我就使用rosrun image_view image_view image:=/body_pose_tester/processed_image
                                发现摄像头就消失了,也没有发现出现被识别出的人体特征位置的照片
                                您能否为解答一下吗?
                                我注释这句话<include file="$(find xiaoqiang_tts)/launch/tts_xunfei.launch" /–>

                                yellow 1 Reply Last reply Reply Quote 0
                                • yellow
                                  yellow last edited by

                                  This post is deleted!
                                  1 Reply Last reply Reply Quote 0
                                  • yellow
                                    yellow @marcos452 last edited by

                                    @marcos452 你好 请问你解决了这个问题吗 我也遇到了此问题

                                    weijiz 1 Reply Last reply Reply Quote 0
                                    • weijiz
                                      weijiz @yellow last edited by

                                      @yellow launch文件内的图像话题要改成kinect的图像话题

                                      1 Reply Last reply Reply Quote 0
                                      • First post
                                        Last post
                                      Copyright © 2015-2021 BlueWhale community