5.5.8 - June 13, 2022 - Code Project’s SenseAI Version 1 - See V2 here https://ipcamtalk.com/threads/codeproject-ai-version-2-0.68030/

Yeah I just looked. At $59.99 atm. Only issue is the lack of 1 click support for installation on Code Project's Sense AI. Once we have that, we're laughing.
 
  • Like
Reactions: fenderman
Yeah I just looked. At $59.99 atm. Only issue is the lack of 1 click support for installation on Code Project's Sense AI. Once we have that, we're laughing.
Yeah, I have been seeing and counting on the "official" $59.99 price (on the main Google Coral website) for the last several weeks, but then realized that that green "Buy" button isn't a direct purchase button: it then shows several companies to buy from, but essentially all of them are either out of stock or much higher in price.
 
  • Like
Reactions: CCTVCam
Yeah I haven't seen it anywhere near $59 yet, but from what I'm seeing it can currently be somewhat widely found for ~$105-ish. Granted that's still a huge percentage increase, but it's a heck of a lot better than ~300+% markups previously seen and given the investment I've already made in server hardware I'd pay that to have a massive increase in my analyzing throughput for sure
 
  • Like
Reactions: CCTVCam
Am I blind or where is the list of models/labels that yolov5l supports/detects? I've got some Christmas deer in my front yard that are being detected as a giraffe -_-
 
  • Haha
Reactions: sebastiantombs
Am I blind or where is the list of models/labels that yolov5l supports/detects? I've got some Christmas deer in my front yard that are being detected as a giraffe -_-
List of the COCO Object Classes The COCO dataset classes for object detection and tracking include the following pre-trained 80 objects:

'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis','snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
 
List of the COCO Object Classes The COCO dataset classes for object detection and tracking include the following pre-trained 80 objects:

'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis','snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
giraffe but no deer? Not in my neighborhood!
 
@1fxman Are you using substream to do AI?

The above behavior is indicative of using main camera stream. Do a search, there's been other posts on this.
Yes, I checked my camera sittings to make sure the “use main camera stream” was not checked. I did edgeicate myself on the main and sub stream issue somewhat. But to make sure I’m going to recheck it.
 
List of the COCO Object Classes The COCO dataset classes for object detection and tracking include the following pre-trained 80 objects:

'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis','snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
So Mike, anyway to add "Deer"? Right now I'm running both Yolov5l ,and IPcam -combined for deer, but I think it would be better cpu wise to only have to use Yolov5l?
 
@1fxman Can you confirm that you have configured both main and substream for your camera? Then the AI will use the substream if you have “use main camera stream” not checked.
 
  • Like
Reactions: 1fxman
I had that problem from using AI on all my cams. I only have 4 using AI and I added a GPU and most of my lag is gone.
Thanks for the response. I have 13 cameras going and plan on adding more (cameras still in boxes). I thinking you may be right about the GPU. But wondering if it could be slow internet on my part. And it’s slooooooooooow. I did notice that the CPU really jumps up when I run AI analytics.