LIVE OBJECT DETECTION USING DEEP LEARNING
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to per-form detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
Object Detection is the process of finding and recognizing real-world object instances.
Technology and Tools:
Ai | Image Processing | Machine Learning | Deep Learning | Python | OpenCv | Raspberry Pi | Vnc Viewer | L298 Motor Driver | USB Camera
OPEN CV | NUMPY | PYTHON|INSTALL SOFTWARE USED PIP COMMAND PROMPT | OPEN CV IMAGE PROCESSING | BGR TO GRAY | BGR TO HSV | LOWER & UPPER RED COLOR IMAGE MASK |INTERFACE WITH USB CAMERA
DEEP LEARNING BASED OBJECT DETECTION USING YOLO ALGORITHM:
GRID INPUT |BOUNDING BOX | CONFIDENCE
TRAFFIC DENSITY IDENDIFY USING DEEP LEARNING:
DETECT TRAFFIC DENSITY | COUNT VEHICLE USING DEEP LEARNING | DISPLAY THE VEHICLE COUNT
TEXT TO SPEECH USING PYTHON PYTTSX3:
PIP INSTALL PYTTSX3 | PIP INSTALL PYPIWIN32 FILE | TEXT TO SPEECH USING
REAL TIME OBJECT DETECTION USING DEEP LEARNING:
PIP INSTAL IMUTILS | RUN CAFÉ MODEL | DETECT OBJECT USING NEURAL NETWORK | OBJECT NAME PLAYING AUDIO OUTPUT
The functional use case attempted in this workshop involved the detection of vehicles and pedestrians from a drone or aerial vehicle. The training data was more skewed towards cars as opposed to other objects of interest since it was hand crafted from videos. The use case could be further expanded for video surveillance and tracking.
Workshop date will be updated soon!