Convolutional Neural Network (CNN) Image Classifier

Demo

Neural network classification method based on SqueezeNet. Images are captured by the camera processed and classified by the S32V processor and then displayed on the TV monitor with a confidence percentage calculated for each object visualized.

Based on SqueezeNet, 501x fewer parameters than AlexNet
Low power consumption - Less than 10 watts total
Average top 1 accuracy of 58% and top 5 accuracies of 92%
CNN built with APEX-DNN library

Product	Link
S32V Vision and Sensor Fusion Evaluation Board	https://www.nxp.com/design/development-boards/automotive-development-platforms/s32v-mpu-platforms/s3...
S32V234	S32V234 Vision Processor \| NXP

Convolutional Neural Network (CNN) Image Classifier

Convolutional Neural Network (CNN) Image Classifier

Convolutional Neural Network (CNN) Image Classifier

Automotive