From da9a885b298a5780fe27742522b0f8f25c94a2e0 Mon Sep 17 00:00:00 2001 From: david Date: Fri, 11 Aug 2023 10:11:47 -0700 Subject: [PATCH] fix links --- shieldbot.md | 2 -- smart-factory-with-tda4vm.md | 2 +- solar-panel-defect-detection.md | 2 +- 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/shieldbot.md b/shieldbot.md index 28a76676..9d853381 100644 --- a/shieldbot.md +++ b/shieldbot.md @@ -61,6 +61,4 @@ By building a security camera on top of a robot, a single camera can cover a lar The machine learning models were very simple to build and train using Edge Impulse's slick interface. They performed very well in my tests, consistently detecting audio anomalies and people. In the future, I would like to enhance Shield Bot's navigation abilities. While on patrol, the robot drives until it encounters an object, then turns in a different direction and continues on. I would like to involve computer vision in this process so that the robot can intelligently cover a space in the most efficient manner. -The source code for Shield Bot is available here: [https://drive.google.com/file/d/16_m-E8TxYmJd3IJF4O6vGs-WlBiBXWyL/view?usp=sharing](https://drive.google.com/file/d/16_m-E8TxYmJd3IJF4O6vGs-WlBiBXWyL/view?usp=sharing) - Link to video: [https://www.youtube.com/watch?v=aZt6PIywaTQ](https://www.youtube.com/watch?v=aZt6PIywaTQ) diff --git a/smart-factory-with-tda4vm.md b/smart-factory-with-tda4vm.md index 7425b35f..49117af3 100644 --- a/smart-factory-with-tda4vm.md +++ b/smart-factory-with-tda4vm.md @@ -40,7 +40,7 @@ Since I was planning on running an RTSP stream, I didn't connect a USB or Raspbe ## RTSP Streaming -Before building my Edge Impulse model, I wanted to ensure that I could get RTSP streaming up and running, which proved to be a bit of a challenge. I've had [success on other projects](https://www.hackster.io/justinelutz/protect-your-casa-with-hasa-38b32e) using a commercial RTSP streaming camera out of the box, but they were not working with the SK-TDA4VM. I reached out to TI's E2E technical forum, and they were prompt in responding to my issues. The technical team recommended [following this tutorial](https://gist.github.com/Santiago-vdk/80c378a315722a1b813ae5da1661f890) on setting up an RTSP streamer in Ubuntu. My thread on the E2E forum can be [found here](https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1196339/sk-tda4vm-unable-to-run-rtsp-streaming-demo?tisearch=e2e-sitesearch&keymatch=tda4vm%20rtsp#). I ended up using my Seeed Studio reComputer 1010 (with a Jetson Nano) with an inexpensive USB camera as my setup for the RTSP streamer. Following the instructions of the tutorial, I was able to get the test source working. +Before building my Edge Impulse model, I wanted to ensure that I could get RTSP streaming up and running, which proved to be a bit of a challenge. I've had [success on other projects](https://www.hackster.io/justinelutz/protect-your-casa-with-hasa-38b32e) using a commercial RTSP streaming camera out of the box, but they were not working with the SK-TDA4VM. I reached out to TI's E2E technical forum, and they were prompt in responding to my issues. My thread on the E2E forum can be [found here](https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1196339/sk-tda4vm-unable-to-run-rtsp-streaming-demo?tisearch=e2e-sitesearch&keymatch=tda4vm%20rtsp#). I ended up using my Seeed Studio reComputer 1010 (with a Jetson Nano) with an inexpensive USB camera as my setup for the RTSP streamer. Following the instructions of the tutorial, I was able to get the test source working. The next challenge was correctly forming the gstreamer pipeline to correctly receive the RTSP stream. That proved a bit of a challenge (for a gstreamer noob like me) and after much trial and error was able to run an RTSP stream on the SK-TDA4VM! Below is the gstreamer pipeline that worked for me for the RTSP streamer example: diff --git a/solar-panel-defect-detection.md b/solar-panel-defect-detection.md index c6ba57fd..bfd6bb26 100644 --- a/solar-panel-defect-detection.md +++ b/solar-panel-defect-detection.md @@ -79,7 +79,7 @@ Then go to *Labeling queue* in the *Data acquisition* section to draw bounding b ![](.gitbook/assets/solar-panel-defect-detection/labeling.jpg) -You can read more about the Labeling queue at this link: [(https://docs.edgeimpulse.com/docs/edge-impulse-studio/data-acquisition/labeling-queue)]((https://docs.edgeimpulse.com/docs/edge-impulse-studio/data-acquisition/labeling-queue)) +You can read more about the Labeling queue at this link: [https://docs.edgeimpulse.com/docs/edge-impulse-studio/data-acquisition/labeling-queue](https://docs.edgeimpulse.com/docs/edge-impulse-studio/data-acquisition/labeling-queue) In the Labelling queue, all the raw images are shown, and we need to drag and drop the markings and label the cracks.