Related Objects of Interest: stop, keep right, no entry, priority road, keep left, car, pedestrians, slippery road, no vehicles, building
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.
by LeeM
3762 images 35 classes
acorn-woodpecker annas-hummingbird blue-jay blue-winged-warbler carolina-chickadee carolina-wren chipping-sparrow common-eider common-yellowthroat dark-eyed-junco eastern-bluebird eastern-towhee harris-hawk hermit-thrush indigo-bunting juniper-titmouse northern-cardinal northern-mockingbird northern-waterthrush orchard-oriole
by osmando
706 images 1342 classes
animal car drink mushroom rock wine glass 2 bottles on a rock next to fruit in front of orange background. 2 brown paper boxes in front of light brown background 2 cream bottles in front of blue tiles 2 macarons on a rock block in front of light orange background 3 black bottles next to yellow stairs and dry flower with shadow 3 blue bottles on blue plates next to dry nuts 3 bottles in front of light background with shadows 3 bottles in front of light brown background with shadows. 3 bottles in front of light gray background with shadows of a plant. 3 boxes in front of dark background 3 perfume bottles on reflective gray surface 4 paper boxes in front of light yellow background 4 potteries on a marble table 6 white bowls of spices on a wooden surface
by hoang quang
1452 images 1513 classes
.6R1.6B-Argiphysol (H/12vỉ x 5v nang mềm) -Hộp- Hà tây 10R1 10R1-5B-Ospay Baby (Lọ 15ml) -Lọ- Trường Thọ 10R1.10C-KĐR Sensodyne-Fresh Mint (Tub 100g)-Thái Lan 10R1.11B-Kamazitap10g Celia- (Hadophar)-tuýp 10R1.11D-KĐR Sensodyne - Gentle Whitening 10R1.12B-Kem nghệ Thái dương 10R1.13A-Kem em bé 20g CVI 10R1.13C-KĐR Sensodyne RAPID Action--giảm ê buốt 10R1.14Aa-Kem nghệ YooSun 25g 10R1.14Ca-KĐR Lacalut aktiv - Đỏ 10R1.15B-KĐR Thái Dương tub 150g 10R1.15D-KĐR Ngọc Châu Tub 125g- Hoa Linh 10R1.1D-Tinh Dầu Tràm Bé Thơ (Lọ 100ml) 10R1.2D-Remos(xịt muỗi) lọ 70ml - Rohto 10R1.3D-Tinh dầu Tràm Bé Thơ 50ml 10R1.4A-Sữa tắm Tây Thi (Lọ 200g) -Hộp- Thái Dương 10R1.4Ca-Zuchi Family (Giầy) (Lọ 50ml - 10lo/Cầu) - Hoa Linh 10R1.5D-Listerine CoolMint (Chai 250ml)-chai-Thái Lan 10R1.611Bc-Xịt mũi Vinasat NL 75ml (xanh)
106 images 3398 classes
by MIS326
715 images 43 classes
1570 images 189 classes
15 degrees ABS malfunction ACC Status Indicator (Active_135) ACC Status Indicator (Active_8) ACC Status Indicator (Standby_135) ACC Status Indicator (Standby_8) ACC driver overtaking ACC driver takes over cue AEB Off indicator AUTO mode_vehicle mode Abnormal status of low-voltage power supply system Abnormal tire pressure Advance charging indicator Automatic parking activation Automatic parking on indicator Battery heating Brake system malfunction or low brake fluid level Brake system warning light CLTC Car model with low light on
by TSR
2930 images 44 classes
Ahead only Beware of ice-snow Bicycles crossing Bumpy road Children crossing Dangerous curve to the left Dangerous curve to the right Double curve End of all speed and passing limits End of no passing End of no passing by vehicles over 3 End of no passing by vehicles over 3.5 metric tons End of speed limit -80 km-h- General caution Go straight or left Go straight or right Keep left Keep right No entry No passing
by soochow
1746 images 61 classes
by SAG
2300 images 23 classes
Ahead only Beware of ice or snow Bicycles crossing Bumpy road Children crossing Dangerous curve left Dangerous curve right Double curve End no passing vehicle with a weight greater than 3.5 tons End of no passing End of speed limit 80kmh End speed and passing limits General caution Go straight or left Go straight or right Keep left Keep right No entry No passing No passing veh over 3.5 tons
87 images 13 classes
89 images 7 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
by FelixProject
506 images 43 classes
Ahead only Beware of ice-snow Bicycles crossing Bumpy road Children crossing Dangerous curve to the left Dangerous curve to the right Double curve End of all speed and passing limits End of no passing End of no passing by vehicles over 3-5 metric tons End of speed limit (80km-h) General caution Go straight or left Go straight or right Keep left Keep right No entry No passing No passing for vehicles over 3-5 metric tons
by Traffic Sign
588 images 47 classes
roundabout Ahead Only Beware of Snow/Ice Bumpy Road Cautionary Road Sign Crossroads Ahead Cycle Crossing End-of-no-passing Give way Left Zigzag Bend No Entry No Overtaking No Overtaking By Heavy Goods Vehicles No Speed Limit No Trucks Allowed No Vehicles Other Danger Prevents Vehicles From Entering Priority Intersection Sign Priority Road
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("leem-pf8fb").project("bird-v2")
snow_model = project.version(2).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
)