Top Defect Computer Vision Models
The models below have been fine-tuned for various defect 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 defect detection model.
At the bottom of this page, we have guides on how to count defects in images and videos. To learn more about defect detection with computer vision, check out the following resources:
Guide: How to Count Defects with Computer Vision
With a model hosted on Roboflow like the ones above and the open source supervision Python package, you can count defects in your images and videos.
The following code snippet counts the number of defects present in an image.
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 supervision as sv
import roboflow
roboflow.login()
rf = roboflow.Roboflow()
# replace with the defect project you choose above
project = rf.workspace("{{WORKSPACE}}").project("windows_segmentation")
defect_model = project.version(6).model
results = defect_model.predict("defect.jpg").json()
defects = sv.Detections.from_roboflow(results)
# print number of defects
print(len(defects))Guide: How to Count Defects in a Zone
With a bit more code, you can count the number of defect present in a specific zone of your image or video.
The following code snippet counts the number of defect present in each frame 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.
Read our blog post on counting objects in a zone
import numpy as np
import supervision as sv
import roboflow
SOURCE_VIDEO_PATH = "defect.mp4"
TARGET_VIDEO_PATH = "defect_out.mp4"
# use https://roboflow.github.io/polygonzone/ to get the points for your shape
polygon = np.array([
# draw 50x50 box in top left corner
[0, 0],
[50, 0],
[50, 50],
[0, 50]
])
roboflow.login()
rf = roboflow.Roboflow()
# replace with the defect project you choose above
project = rf.workspace("{{WORKSPACE}}").project("windows_segmentation")
defect_model = project.version(6).model
# create BYTETracker instance
defect_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 PolygonZone instance
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=(video_info.width, video_info.height))
# create box annotator
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
colors = sv.ColorPalette.default()
# create instance of BoxAnnotator
zone_annotator = sv.PolygonZoneAnnotator(thickness=4, text_thickness=4, text_scale=2, zone=zone, color=colors.colors[0])
# 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 = defect_model.predict(frame).json()
defects = sv.Detections.from_roboflow(results)
# show defect detections in real time
print(defects)
# tracking defect detections
defects = defect_tracker.update_with_detections(defects)
annotated_frame = box_annotator.annotate(scene=frame, detections=defects)
annotated_frame = zone_annotator.annotate(scene=annotated_frame)
# return frame with box and line annotated result
return annotated_frame
# process the whole video
sv.process_video(
source_path = SOURCE_VIDEO_PATH,
target_path = TARGET_VIDEO_PATH,
callback=callback
)Guide: How to Track Defects Crossing a Line
You can count how many defects have crossed a line using the supervision LineCounter method.
The following code snippet counts the number of defects 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 = "defect.mp4"
TARGET_VIDEO_PATH = "defect_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 defect project you choose above
project = rf.workspace("{{WORKSPACE}}").project("windows_segmentation")
defect_model = project.version(6).model
# create BYTETracker instance
defect_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 = defect_model.predict(frame).json()
defects = sv.Detections.from_roboflow(results)
# show defect detections in real time
print(defects)
# tracking defect detections
defects = defect_tracker.update_with_detections(defects)
annotated_frame = trace_annotator.annotate(
scene=frame.copy(),
detections=defects
)
annotated_frame=box_annotator.annotate(
scene=annotated_frame,
detections=defects
)
# update line counter
line_zone.trigger(defects)
# 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
)