#!/usr/bin/env python
# coding: utf-8

# # Object Detection from Videos with YOLOv5
# 
# In this tutorial, we will use fastdup with a pretrained yolov5 object detection model to detect and crop from videos. Following that we analyze the cropped objects for issues such as duplicates, near-duplicates, outliers, bright/dark/blurry objects.
# 
# > This is an advanced functionality of fastdup. Sign up for free to be an beta tester and get early access at info@visual-layer.com .

# ## Installation & Setting Up

# In[ ]:


get_ipython().system('pip install pip -U')
get_ipython().system('pip install fastdup')


# In[4]:


import fastdup
fastdup.__version__


# ## Download & Extract Dataset

# In[1]:


get_ipython().system('gdown  --fuzzy https://drive.google.com/file/d/1fzmOgmRu557aU4lEbzL7XCf78KntFCeQ/view')


# In[2]:


get_ipython().system('unzip data.zip')


# ## Video to Images
# 
# fastdup works on images. We must first turn the videos into frames of images.
# 
# We can use a one-liner fastdup utility function to turn all the videos in a folder into frames:

# In[5]:


fastdup.extract_video_frames(input_dir="data", work_dir="frames")


# ## Run fastdup
# 
# Now that we have the frames of images, let's run fastdup and analyze the frames.

# In[6]:


fd = fastdup.create(input_dir='frames', work_dir='yolov5_detection_work_dir')


# As this is an advance functionality of fastdup, you'd need a license key to use this function, sign up and get your license key for free at info@visual-layer.com .

# In[7]:


fd.run(bounding_box='yolov5s', license='your_license_key', overwrite=True)


# ## Components Gallery
# 
# We can visualize the cluster of similar detections using the components gallery view. Specify `draw_bbox=True` to see the detection bounding box on the original image.

# In[8]:


fd.vis.component_gallery(draw_bbox=True)


# If you'd like to view just the cropped bounding box images, specify `draw_bbox=False`

# In[9]:


fd.vis.component_gallery(draw_bbox=False)


# ## Find Similar Objects Across Videos
# 
# Using the `similarity_gallery` view, we can find similar looking detections across all the extracted frames.

# In[10]:


fd.vis.similarity_gallery(draw_bbox=False)


# ## Find Outliers
# 
# Useing the `outliers_gallery` we can also visualize detections that looks visually different from others.

# In[11]:


fd.vis.outliers_gallery()


# ## Duplicate Detections
# 
# With the `duplicates_gallery` view, visualize duplicate image pairs across videos.

# In[12]:


fd.vis.duplicates_gallery()


# In[ ]:





# ## Dark Detections
# 
# Using the `stats_gallery` view, we can sort the detections following a desired `metric` such as 'dark', 'bright' and 'blur'. 

# In[13]:


fd.vis.stats_gallery(metric='dark')


# ## Bright Detections

# In[14]:


fd.vis.stats_gallery(metric='bright')


# ## Blurry Detections

# In[15]:


fd.vis.stats_gallery(metric='blur')


# In[ ]: