Re-Identification with RaspberryPi and NCS2

Person re-identification is a computer vision technique that aims to identify individuals across different camera views or over time.
The technique has proven to be an effective solution for monitoring and tracking customer behavior in retail shops. By implementing this technology in a shop, we were able to gain valuable insights into customer preferences, behaviors, and traffic flow, which we used to optimize the shop layout, improve customer experience, and increase revenue.

Re-Identification model output

Benchmarks

Include the benchmark results of running multiple model precisions. The CPU used was Intel® Core™ i3-8350K CPU @ 4.00GHz × 4 and 16 GB Ram

For Detection model

Properties	CPU	NCS with CPU	NCS2 with Raspberry
Model Loading	0.180	2.149	–
Infer Time	0.021	0.033	–
FPS	26.466	8.449	–

For Re-Idendification model

Properties	CPU	NCS with CPU	NCS2 with Raspberry
Model Loading	0.277	2.203	–
Infer Time	0.019	0.115	–
FPS	32.54	5.971	–

Our customers are our biggest fans

Hear from the clients we have worked with

"I highly recommend LvisionAI for their efficient, motivated, and professional approach in deploying our model code into a functional model server, making our collaboration a positive experience.“"

"I was interested in the practical implementation of deep learning plus computer vision and LvisionAI has helped me a great deal on this. Shahid and the team are very professional and accommodating to my needs. The communication was clear and all the deliverables are on time. I look forward to using LvisionAI service again and would recommend them to friends!"

"The LvisionAI team is skilled and reliable in developing custom deep learning applications. They are consistently hardworking in developing long term client projects. I would highly recommend them."