Jetson Nano Detection and Tracking

stevenmacenski · July 13, 2019, 12:01am

Installing and setting up the new Nvidia Jetson Nano was surprisingly time consuming and unintuitive. From protobuf version conflicts, to Tensorflow versions, OpenCV recompiling with GPU, models running, models optimized, and general chaos in the ranks.

This repository is my set of install tools to get the Nano up and running with a convincing and scalable demo for robot-centric uses.

jetsonvzqvp · July 20, 2019, 8:55pm

Nice, will keep an eye on it. Having some trouble myself.

jetsonvzqvp · July 21, 2019, 1:45am

I was able to modify this to get an rtsp feed working from a wyze cam. Thanks again for this, save me countless hours.

stevenmacenski · July 21, 2019, 3:06am

Awesome! I’m glad you got some use out of it. I’m curious, what’s your application?

Best!
Steve

jetsonvzqvp · July 21, 2019, 3:40am

Detect presence of community cat to control small outdoor fan during the summer.

stevenmacenski · July 21, 2019, 3:46am

That’s super awesome! Glad that I could help.

kerron.manwaring · August 15, 2019, 3:02pm

Gonna give this a try

consultorsmartcities · September 12, 2019, 4:24am

The algorithm works perfectly.
How can I make it work with an IP camera?
I view my IP camera with:
cap = cv2.VideoCapture (“rtsp: // admin: admin@192.168.1.130: 554 / cam / realmonitor? channel = 1 & subtype = 1”).

stevenmacenski · September 12, 2019, 4:50am

You can change this line here with your new capture mode:

github.com

SteveMacenski/jetson_nano_detection_and_tracking/blob/main/src/mipi_camera.py#L22


      
          def __init__(self, width=300, height=300):
              self.cap = None
              self.width = width
              self.height = height
          
          
def _gstStr(self, width, height):
              return 'nvarguscamerasrc ! video/x-raw(memory:NVMM), width=%d, height=%d, format=(string)NV12, framerate=(fraction)%d/1 ! nvvidconv ! video/x-raw, width=(int)%d, height=(int)%d, format=(string)BGRx ! videoconvert ! appsink' % (3280, 2464, 21, width, height)
          
          
def startStreaming(self):
              print ("Starting to stream camera...")
              self.cap = cv2.VideoCapture(self._gstStr(self.width, self.height))
          
          
def getFrame(self):
              rtn_val, frame = self.cap.read()
              if rtn_val:
                  return frame
              else:
                  print ("Failed to capture frame!")
                  return None
          
          
def isOpened(self):

consultorsmartcities · September 12, 2019, 6:09pm

Thank you very much for your previous response.
Now I work with the IP camera at the beginning, and then the following came out:
Debug: Running at: 8.329104874774611 Hz.
Debug: Found objects: person.
Debug: Running at: 9.681494082806092 Hz.
[NULL @ 0x2bc0c6f0] missing picture in access unit
Debug: Found objects: person.
Debug: Running at: 8.944051485342756 Hz.
Debug: Found objects: person.
Debug: Running at: 9.135469144434062 Hz.
Debug: Found objects: person.
Debug: Running at: 8.874504891837908 Hz.
Debug: Found objects: person.
Debug: Running at: 9.270204442479832 Hz.
Failed to capture frame!
Traceback (most recent call last):
File “jetson_live_object_detection.py”, line 89, in
live_detection.start()
File “jetson_live_object_detection.py”, line 59, in start
scores, boxes, classes, num_detections = self.detector.detect(img)
File “/home/dlinano/jetson_nano_detection_and_tracking/src/object_detector.py”, line 24, in detect
scores, boxes, classes, num_detections = self.tf_sess.run(self.tf_tensors, feed_dict={self.tf_input: img_expanded})
File “/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py”, line 929, in run
run_metadata_ptr)
File “/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py”, line 1121, in _run
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
File “/usr/local/lib/python3.6/dist-packages/numpy/core/_asarray.py”, line 85, in asarray
return array(a, dtype, copy=False, order=order)
TypeError: int() argument must be a string, a bytes-like object or a number, not ‘NoneType’

jordanmicahbennett · October 8, 2019, 2:54pm

Thanks for your guide.
This worked for me, as I underline here: [url]https://github.com/JordanMicahBennett/live_ai_object-detection-on-tiny-jetson-neural-nano-computer[/url]

bakkeg1 · August 31, 2020, 1:07am

Hi there,

I am trying to run this on Ubuntu 18.04, with the Jetpack 4.4 & Deepstream SDK 5.0. Everything installed correctly up until I try run the models. Once I do I get this error:

"ImportError: libcublas.so.10.0: cannot open shared object file: No such file or directory

Failed to load the native TensorFlow runtime.

See Build and install error messages | TensorFlow"

Anyone have a clue why? Thanks!

Topic		Replies	Views
Wildlife Documentation Camera Jetson Nano	8	1555	October 18, 2021
Object detection and recording video Jetson Nano jetson-inference	11	1936	April 25, 2022
Nvidia jetson detectnet increasing latency Jetson Nano jetson-inference , ai	9	1689	October 15, 2021
IP camera connection with jetson.utils.gstCamera Jetson Nano camera	14	2579	October 15, 2021
Very bad performance, or is something wrong? Jetson Nano	10	1057	April 30, 2023
IP Camera with Jetson Nano Jetson Nano	20	20777	October 14, 2021
Capture-camera does not work Jetson Nano	25	2521	October 14, 2021
Recommendation of an existing application for object detection and tracking with jetson Nano, YOLO V3 Tiny and Tensorflow Jetson Nano tensorflow	17	1865	October 12, 2021
Detecting objects from RSTP Stream (IP Camera) Jetson Nano rtsp , camera , gstreamer	17	5154	October 15, 2021
DeepStream on Jetson Nano - object detection Jetson Nano	17	5304	October 15, 2021

Jetson Nano Detection and Tracking

Related topics