refine video file

README.md

@@ -3,7 +3,7 @@ Grounded SAM 2: Ground and Track Anything with Grounding DINO, Grounding DINO 1.
 
 Grounded SAM 2 does not introduce significant methodological changes compared to [Grounded SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything). Both approaches leverage the capabilities of open-world models to address complex visual tasks. Consequently, we try to **simplify the code implementation** in this repository, aiming to enhance user convenience.
 
-[![Video Name](./notebooks/videos/bedroom/00000.jpg)](https://github.com/user-attachments/assets/83675ffd-86d8-439d-ac95-4dfb339e181a)
+[![Video Name](./notebooks/videos/bedroom/00000.jpg)](./demo_images/children_tracking_demo.mp4)
 
 ## Contents
 - [Installation](#installation)

video_utils.py

@@ -2,34 +2,34 @@ import cv2
 import os
 from tqdm import tqdm
 
-def create_video_from_images(image_folder, output_video_path, frame_rate=30):
+def create_video_from_images(image_folder, output_video_path, frame_rate=25):
-    # 定义允许的图像后缀
+    # define valid extension
     valid_extensions = [".jpg", ".jpeg", ".JPG", ".JPEG"]
     
-    # 获取图像文件列表
+    # get all image files in the folder
     image_files = [f for f in os.listdir(image_folder) 
                    if os.path.splitext(f)[1] in valid_extensions]
-    image_files.sort()  # 排序，确保按正确的顺序读取图像
+    image_files.sort()  # sort the files in alphabetical order
     print(image_files)
     if not image_files:
         raise ValueError("No valid image files found in the specified folder.")
     
-    # 读取第一张图像以获取视频尺寸
+    # load the first image to get the dimensions of the video
     first_image_path = os.path.join(image_folder, image_files[0])
     first_image = cv2.imread(first_image_path)
     height, width, _ = first_image.shape
     
-    # 创建视频写入对象
+    # create a video writer
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # 可以选择其他编码方式，如 'XVID'
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v') # codec for saving the video
     video_writer = cv2.VideoWriter(output_video_path, fourcc, frame_rate, (width, height))
     
-    # 逐帧写入视频
+    # write each image to the video
     for image_file in tqdm(image_files):
         image_path = os.path.join(image_folder, image_file)
         image = cv2.imread(image_path)
         video_writer.write(image)
     
-    # 释放资源
+    # source release
     video_writer.release()
     print(f"Video saved at {output_video_path}")