ffzj's profile - activity

how can i get the internal parameters of the kinect camera in the kinect_gazebo.xacro file? I add the kinect camera in t

how can i get the internal parameters of the kinect camera in the kinect_gazebo.xacro file? I add the kinect camera in t

how can i get the internal parameters of the kinect camera in the kinect_gazebo.xacro file? I add the kinect camera in t

I use the tensorflow object detection API train a model, I want to use the image topic in the kinect camera and identify it with the trained model. I found that recognition is much less effective than using image recognition directly. Why is that? Is it caused by predicting the image in rosimage format after converting it to cv::mat? Is there any way to solve it?

image_topic = "/kinect2/qhd/image_color"

self._cv_bridge = CvBridge()

self._sub = rospy.Subscriber(image_topic, Image, self.mycallback, queue_size=1) 

def mycallback(self,image):

    cv_image = self._cv_bridge.imgmsg_to_cv2(image_msg, "bgr8")
    pil_img = Image.fromarray(cv_image)

I have solved the problem, bgr8 is not the suitable type foe the model ,i have changed the cv_image type to rgb8.

use objectdetection model predict the image subscribed by kinect topic I use the tensorflow object detection API train a

use objectdetection model predict the image subscribed by kinect topic I use the tensorflow object detection API train a

use objectdetection model predict the image subscribed by kinect topic I use the tensorflow object detection API train a

I use python publish a msg like this:

InfoData.msg
    int32 Num
    string color
    string name
 InfoDataArray.msg
   InfoData[] Infos

Now I want to use C++ subscribe the InfoDataArray.mag and store in the Structure. how to do this ?

How to use C++ subscribe to a custom msg array published by Python I use python publish a msg like this: InfoData.msg