Community Articles
Find and share helpful community-sourced technical articles
Announcements
Alert: Welcome to the Unified Cloudera Community. Former HCC members be sure to read and learn how to activate your account here.
Labels (1)
Super Guru

93176-fcn2.png

In preparation for my talk at the Philadelphia Open Source Conference(https://phillyopensource.splashthat.com/), Apache Deep Learning 201, I wanted to have some good images for running various Apache MXNet GluonCV Deep Learning Algorithms for Computer Vision. See: https://gluon-cv.mxnet.io/

Using Apache open source tools - Apache NiFi 1.8 and Apache MXNet 1.3 with GluonCV I can easily ingest live traffic camera images and run Object Detection, Semantic Segmentation and Instance Segmentation.

Code: https://github.com/tspannhw/ApacheDeepLearning201

It's so easy, I am running multiple on the data to see which gives me the results I like. I am like YOLO which is a one of my old favorites.

  • yolonifitraffic.py
  • demo_mask_rcnn_nyc.py
  • demo_deeplab_nyc.py

So we can find the cars and people in these webcams. Use cases can be around traffic optimization, public safety and advertisement optimization. Due to licensing, I thought it better not to show Traffic Camera data here.

To industrialize and scale out this process from a single Data Scientist to a national ingestion system, we use the power of Apache NiFi to ingest, process and control flows. I am using the latest Apache NiFi 1.8.

Apache NiFi Flow to Ingest and Process Traffic Camera Data

93184-street1.png

First we have a list of URLs that I want to process, this can be sourced and stored anywhere. For ease of use with a static set I am using GenerateFlowFile. I have a JSON file of URLs that I split and parse to call various Computer Vision Python scripts (DeepLab3, MaskRCNN, YOLO and others). YOLO seems to be the most useful so far. I am grabbing the results, some system metrics, metadata and the deep learning analytics generated by Apache MXNet.

93183-street2.png

I split the flow into two portions. One builds GluonCV result data from YOLO and the other creates a file from TensorFlow results done on the fly.

Here is a list of my webcam URLs. There's millions of them out there.


93177-allthecameras.png

If your data is tabular, then you need a schema for fast record processing.

93178-streetschema.png

An Example Dataset Returned from GLUONCV - YOLO Python 3.6 Script

93179-streetdata.png

I turn JSON data into HDFS Writeable AVRO Data and Can Run Live SQL on It

93180-street6.png

One Output Source Code Be a Joint Slack Group

93181-street3.png

Object Detection: GluonCV YOLO v3 and Apache NiFi

This can be OpenCV, a static photo or from a URL.

93172-picture4.png

Object Detection: Faster RCNN with GluonCV

Faster RCNN model trained on Pascal VOC dataset with ResNet-50 backbone

net = gcv.model_zoo.get_model(faster_rcnn_resnet50_v1b_voc, pretrained=True)

https://gluon-cv.mxnet.io/api/model_zoo.html93169-picture1.png


Instance Segmentation: Mask RCNN with GluonCV

Mask RCNN model trained on COCO dataset with ResNet-50 backbone

net = model_zoo.get_model('mask_rcnn_resnet50_v1b_coco', pretrained=True)

https://gluon-cv.mxnet.io/build/examples_instance/demo_mask_rcnn.html

https://github.com/matterport/Mask_RCNN

https://arxiv.org/abs/1703.06870

93173-people.png

Photo by Ryoji Iwata on Unsplash

There's a lot of people crossing the street!

Semantic Segmentation: DeepLabV3 with GluonCV

GluonCV DeepLabV3 model on ADE20K dataset

model = gluoncv.model_zoo.get_model('deeplab_resnet101_ade', pretrained=True)

run1.sh demo_deeplab_webcam.py

This runs pretty slow on a machine with no GPU.

https://www.cityscapes-dataset.com/

http://groups.csail.mit.edu/vision/datasets/ADE20K/

https://arxiv.org/abs/1706.05587

https://gluon-cv.mxnet.io/build/examples_segmentation/demo_deeplab.html

93170-picture2.png

That is the best picture of me ever!


Semantic Segmentation: Fully Convolutional Networks

GluonCV FCN model on PASCAL VOC dataset

model = gluoncv.model_zoo.get_model(‘fcn_resnet101_voc ', pretrained=True)

run1.sh demo_fcn_webcam.py

https://gluon-cv.mxnet.io/build/examples_segmentation/demo_fcn.html

https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf

93171-picture3.png

It found me.


For NYC Dot and PennDot camera usage, you have to sign a developer agreement for a feed!

See:

http://www.nyc.gov/html/dot/html/home/home.shtml

https://www.penndot.gov/Pages/default.aspx


street3.png
349 Views
Don't have an account?
Coming from Hortonworks? Activate your account here
Version history
Revision #:
2 of 2
Last update:
‎08-17-2019 05:42 AM
Updated by:
 
Contributors
Top Kudoed Authors