HSRW EOLab Students Wiki

User Tools

Site Tools

Trace:
amc:ss2025:group-e:start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
amc:ss2025:group-e:start [2025/07/29 17:11] – 35983_students.hsrwamc:ss2025:group-e:start [2025/07/29 17:23] (current) – 35983_students.hsrw
Line 89: Line 89:
 ==== Files Setup and Execution === ==== Files Setup and Execution ===
 Provided below is a downloadable ZIP containing the pre-trained COCO object detection model used in this setup. It also includes a list of all detectable object classes that the COCO library has been trained to recognize. All project files, including the object detection, dashboard scripts and vehicle log, were placed into the previously downloaded archives (Object_Detection_Files) and transferred to the Raspberry Pi Desktop using a USB stick. Provided below is a downloadable ZIP containing the pre-trained COCO object detection model used in this setup. It also includes a list of all detectable object classes that the COCO library has been trained to recognize. All project files, including the object detection, dashboard scripts and vehicle log, were placed into the previously downloaded archives (Object_Detection_Files) and transferred to the Raspberry Pi Desktop using a USB stick.
 +
 {{ :amc:ss2025:group-e:object_detection_files.zip |}} {{ :amc:ss2025:group-e:object_detection_files.zip |}}
 +
 To execute the object detection script, enter the following command in the terminal. To execute the object detection script, enter the following command in the terminal.
 <code C++> <code C++>
Line 123: Line 125:
 # === Load class names === # === Load class names ===
 classNames = [] classNames = []
-classFile = "/home/aless/Desktop/Object_Detection_Files/coco.names"+classFile = "/home/pi/Desktop/Object_Detection_Files/coco.names"
 with open(classFile, "rt") as f: with open(classFile, "rt") as f:
     classNames = f.read().rstrip("\n").split("\n")     classNames = f.read().rstrip("\n").split("\n")
  
 # === Load model config and weights === # === Load model config and weights ===
-configPath = "/home/aless/Desktop/Object_Detection_Files/ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt" +configPath = "/home/pi/Desktop/Object_Detection_Files/ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt" 
-weightsPath = "/home/aless/Desktop/Object_Detection_Files/frozen_inference_graph.pb"+weightsPath = "/home/pi/Desktop/Object_Detection_Files/frozen_inference_graph.pb"
  
 assert os.path.exists(classFile), f"Missing file: {classFile}" assert os.path.exists(classFile), f"Missing file: {classFile}"
Line 471: Line 473:
 Despite these challenges, the project demonstrates that a low-cost and accessible traffic monitoring solution is possible without specialized AI hardware. With further development, such a system could be adapted for real-world use cases in traffic analysis, planning, or environmental studies. Despite these challenges, the project demonstrates that a low-cost and accessible traffic monitoring solution is possible without specialized AI hardware. With further development, such a system could be adapted for real-world use cases in traffic analysis, planning, or environmental studies.
 ===== Video ===== ===== Video =====
 +{{ :amc:ss2025:group-e:carpi_video.mp4 |}}
  
 ===== References ===== ===== References =====
--insert info +COCO - Common Objects in Context. (n.d). https://cocodataset.org/#home
  
  
amc/ss2025/group-e/start.1753801880.txt.gz · Last modified: 2025/07/29 17:11 by 35983_students.hsrw