Open in Colab

Modern Dashboards can accommodate a broad array of gauges, climate controls, infotainment, and entertainment systems, which contrast to the earlier simpler controls of only speed, fuel, and oil pressure. Automakers have different and distinct ways of designing their dashboards and using a collection of visual identification tools, machine learning and deep learning algorithms we will learn to leverage vehicle features of the dashboard to identify the vehicle and its characteristics.

The goal of this project is to develop a machine learning model that can help identify the content of a vehicle and its features using visual cues from its interior images of the vehicle. This is a multiclass supervised classification problem that will require labeled images to learn the features from curves, edges, and combination of features. Our dataset consist of images collected from the CompCar dataset.

• Environment: Tensorflow 2.0, Tensorflow JS and Tensorflow Hub
• Vehicle Classification: Previously trained on ImageNet.
• Object detection: model that localize and identify multiple objects in a single image.
• Demo

This repo was created as a summer practicum project. Image Classification is applied to interior vehicle images from 3 different Makes using tensorflow.js and Google Colab. It is loosely based on the tfjs Mobilenet example.

1. Image Classification done using a pre-trained model as the base and different classifiers, feature extractors, and fine tuning on a custom dataset. classifier_url = feature_extractor_url =

2. Object Detection Faster RCNN Inception V2 coco
   Single-Shot Multibox Detector (SSD) with feature extraction head from MobileNet
   SSD Lite Mobilenet V2 SSD Mobilenet V2

|Faster_rcnn_inception_v2_coco
|Ssd_inception_v2_coco
Single-Shot Multibox Detector (SSD) with feature extraction head from MobileNet

• Tensorflow Object Detection API
• Tensorflow COCO-SSD
• Steering Ecosystem Simulation Demo

• JS Doodle Classifier video tutorials
• ml4a ofx Doodle Classifier

Stephanie Rogers | [email protected] | [email protected]

Jatin Gongiwala | [email protected] | [email protected]

Ranjitha Vidyashankar | [email protected] | [email protected]