If you or anyone you know works on computer vision models deployed on the edge, would love to understand what type of hardware do you deploy to.
Trying to understand the various options that exist when it comes to deploying computer vision models on devices. Some boards that I am aware of are:
NVIDIA Jetson series
Qualcomm 605 SOC
Raspberry Pi
BeagleBoard
Arducam Pico4ML
But wondering what is the industry standard for applications such as manufacturing robots, drones, autonomous robots that use lidar
we recently switched from Jetson Xavier to Jetson Orin boxes.
And we have a suite of algos. Yolov5 for bboxes, SoloV2 for masks, and Efficientnet for classification. We also use them for image capturing but that’s a bit overkill. They have a full web app stack with db etc and our product’s UI running on them + the inference engine. So pretty capable little boxes.
this is very informative. is there any incentive for you guys to try out new architectures? yolov5 and solov2 are already 4+ years old.