Related Objects of Interest: dusty, defective, bird drop, non defective, electrical damage, physical damage, bird-drop, electrical-damage, non-defective, physical-damage
Top Snow Computer Vision Models
The models below have been fine-tuned for various snow detection tasks. You can try out each model in your browser, or test an edge deployment solution (i.e. to an NVIDIA Jetson). You can use the datasets associated with the models below as a starting point for building your own snow detection model.
At the bottom of this page, we have guides on how to count snow in images and videos.
4320 images 127 classes
by kendrickxy
2312 images 119 classes
roundabout Bump Car breaking Children Crosswinds Curve Cyclist crossing Cyclists Dip Domestic animals End of all previously signed restrictions End of no overtaking End of no overtaking by heavy goods vehicles End of no parking zone End of priority road End of speed limit 30 End of speed limit zone 30 Entering city Exiting city Falling rocks
87 images 6 classes
773 images 24 classes
by Solar Panel
797 images 7 classes
by solar panel
797 images 7 classes
by SolarPanel2
780 images 7 classes
by Jahnavi
570 images 7 classes
by Solar Panel
88 images 7 classes
570 images 7 classes
89 images 7 classes
by Esher Art
258 images 258 classes
E101-MC-Escher-No-101-Lizards-1956 E104-MC-Escher-No-104-Lizard-1959 E105-MC-Escher-No-105-Pegasus-1959 E107-MC-Escher-No-107-Fish-1960 E109-MC-Escher-No-109-Creeping-Creature-1961 E11-MC-Escher-No-11-Sea-Horse-1937-1938 E110-MC-Escher-No-110-BirdFish-1961 E124-MC-Escher-No-124-Lizard-1965 E126-MC-Escher-No-126-FishBird-1967 E15-MC-Escher-No-15-Lizard-1937 E17-MC-Escher-No-17-Eagle-1938 E18-MC-Escher-No-18-Two-Birds-1938 E20-MC-Escher-No-20-Fish-1938 E21-MC-Escher-No-21-IMP-1938 E22-MC-Escher-No-22-BirdFish-1938 E25-MC-Escher-No-25-Lizard-1939 E28-MC-Escher-No-28-Three-Birds-1938 E34-MC-Escher-No-34-BirdFish-1941 E34B-MC-Escher-No-34B-BirdFish-1941 E38-MC-Escher-No-38-Dragonfly-1941
Guide: How to Track Snow Crossing a Line
You can count how many snow have crossed a line using the supervision LineCounter
method.
The following code snippet counts the number of snow that cross a line in a video.
To use the snippet below, you will need to run pip install roboflow supervision
. Replace the project name and model name with any model trained on Universe, such as those listed above.
import numpy as np
import supervision as sv
import roboflow
SOURCE_VIDEO_PATH = "snow.mp4"
TARGET_VIDEO_PATH = "snow_out.mp4"
# use https://roboflow.github.io/polygonzone/ to get the points for your line
LINE_START = sv.Point(0, 300)
LINE_END = sv.Point(800, 300)
roboflow.login()
rf = roboflow.Roboflow()
# replace with the snow project you choose above
project = rf.workspace("screaming-sirens-tcuvm").project("screamin--sirens---footprint-detection")
snow_model = project.version(5).model
# create BYTETracker instance
snow_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
# create VideoInfo instance
video_info = sv.VideoInfo.from_video_path(SOURCE_VIDEO_PATH)
# create frame generator
generator = sv.get_video_frames_generator(SOURCE_VIDEO_PATH)
# create LineZone instance, it is previously called LineCounter class
line_zone = sv.LineZone(start=LINE_START, end=LINE_END)
# create instance of BoxAnnotator
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
# create instance of TraceAnnotator
trace_annotator = sv.TraceAnnotator(thickness=4, trace_length=50)
line_zone_annotator = sv.LineZoneAnnotator(thickness=4, text_thickness=4, text_scale=2)
# define call back function to be used in video processing
def callback(frame: np.ndarray, index:int) -> np.ndarray:
# model prediction on single frame and conversion to supervision Detections
results = snow_model.predict(frame).json()
snow = sv.Detections.from_roboflow(results)
# show snow detections in real time
print(snow)
# tracking snow detections
snow = snow_tracker.update_with_detections(snow)
annotated_frame = trace_annotator.annotate(
scene=frame.copy(),
detections=snow
)
annotated_frame=box_annotator.annotate(
scene=annotated_frame,
detections=snow
)
# update line counter
line_zone.trigger(snow)
# return frame with box and line annotated result
return line_zone_annotator.annotate(annotated_frame, line_counter=line_zone)
# process the whole video
sv.process_video(
source_path = SOURCE_VIDEO_PATH,
target_path = TARGET_VIDEO_PATH,
callback=callback
)