Adaptive Computing Challenge 2021

We hope to build up a system to monitor crowd density near exits and intervene in the crowd behaviour to improve the crowd escape speed

Efficiently computing multi-hash algorithms by time-slicing with fast dynamic function exchange.

A self-built dataset and a GTX1070 graphics card are used to train the CNN network.

real-time pedestrian target detection system dedicated to campus roads

This project demonstrates the ability of the KV260 running Ubuntu to identify LEGO bricks.

This module based on Spinal HDL language, designed a maximum support bandwidth of 100G UDP communication circuit system.

A Gesture-Controlled Self Service Kiosk. Interacting with the computer in a touchless fashion

The project improves the yolo algorithm for dense pedestrian detection models.

LSTM neural network is used to predict financial stock time series.

Let's make ADAS more precise and fast.

Mark the center position of lane line and mark it with blue diamond in the picture

We realize a real-time object detection system with Vitis AI.

convert the steel plate image data into video, process it through Xilinx KRIA kv260, and finally output the image in HDMI

Azure Xilinx DataCenter accelerated ONNX signalR symbol image recognition service for real-time Virtual Breadboard circuit design assist.

Give gamers a way to get more physical activity while playing their favorite AAA game.

Pest infestation detection using Kria KV260

The project uses ResNet50 as the training network, using images of hands that have been labeled with key points as the training set.

Fogged Scene suffers a lot from accidents due to low visibility through it. We here tried to solve such an issue using focusing on realtime.

In this project, we use the VCK 5000 to build a large-scale image retrieval system, which is very useful in many online services.

We are trying to code a 3DOF Robotic ARM integrated with object detection for pick & place operation