1 00:00:00,000 --> 00:00:01,000 Ultralytics. 2 00:00:01,000 --> 00:00:08,000 YOLO 11 is a cutting edge, state of the art computer vision model that is built upon the success of 3 00:00:08,000 --> 00:00:10,000 previous YOLO versions. 4 00:00:11,000 --> 00:00:19,000 YOLO 11 outperforms all the previous models in terms of speed, accuracy, and efficiency, which makes 5 00:00:19,000 --> 00:00:26,000 it an excellent choice for a wide range of object detection, instance segmentation, pose estimation, 6 00:00:26,000 --> 00:00:28,000 and image classification tasks. 7 00:00:29,000 --> 00:00:37,000 Your 11 comes with a faster processing speed, and it is around 2% quicker than YOLO v ten, which makes 8 00:00:37,000 --> 00:00:41,000 it an ideal choice for real time applications. 9 00:00:42,000 --> 00:00:48,000 YOLO 11 is built upon the advancements that are introduced in YOLO v9 and YOLO ten. 10 00:00:49,000 --> 00:00:56,000 YOLO 11 incorporates improved architectural designs, enhanced feature extraction techniques, and optimized 11 00:00:56,000 --> 00:00:57,000 training methods. 12 00:00:58,000 --> 00:01:04,000 YOLO 11 supports a variety of computer vision tasks which include object detection. 13 00:01:04,000 --> 00:01:11,000 In object detection, we identify and locate objects with an image and video frames, and we draw bounding 14 00:01:11,000 --> 00:01:13,000 boxes around each of the detected object. 15 00:01:14,000 --> 00:01:20,000 And in case of object detection, application lies in surveillance, autonomous driving, and retail 16 00:01:20,000 --> 00:01:21,000 analysis. 17 00:01:21,000 --> 00:01:24,000 YOLO 11 also supports instance segmentation. 18 00:01:24,000 --> 00:01:31,000 In instance segmentation, we draw masks around each of the detected object, and the application of 19 00:01:31,000 --> 00:01:36,000 instance segmentation lies in medical imaging and defect detection in manufacturing. 20 00:01:36,000 --> 00:01:39,000 YOLO 11 also supports pose estimation. 21 00:01:39,000 --> 00:01:46,000 In pose estimation, we detect specific key points with an image or video frame to track movements or 22 00:01:46,000 --> 00:01:47,000 poses. 23 00:01:47,000 --> 00:01:53,000 The application of pose estimation lies in sports analytics, healthcare applications, and in fitness 24 00:01:53,000 --> 00:01:54,000 tracking. 25 00:01:55,000 --> 00:01:57,000 YOLO 11 also supports image classification. 26 00:01:57,000 --> 00:02:04,000 In image classification, we categorize entire image into predefined classes, and the application of 27 00:02:04,000 --> 00:02:08,000 image classification lies in e-commerce and wildlife monitoring. 28 00:02:09,000 --> 00:02:12,000 YOLO 11 also provides support for object tracking. 29 00:02:12,000 --> 00:02:18,000 In object tracking, we basically assign a unique ID to each of the detected object, and then we track 30 00:02:18,000 --> 00:02:21,000 that detected object throughout the entire video frames. 31 00:02:23,000 --> 00:02:29,000 In case of if we want to compare the performance of YOLO 11 with other YOLO orders, here you can see 32 00:02:29,000 --> 00:02:31,000 a chart in your screens. 33 00:02:31,000 --> 00:02:37,000 So we can see clearly see that YOLO 11 comes with five different models, and all these five models 34 00:02:37,000 --> 00:02:40,000 outperforms all the other YOLO models. 35 00:02:40,000 --> 00:02:42,000 And you can see here a blue line over here. 36 00:02:42,000 --> 00:02:48,000 And you can clearly see YOLO 11 outperforms all the other YOLO models in terms of accuracy, as well 37 00:02:48,000 --> 00:02:50,000 as in terms of speed. 38 00:02:50,000 --> 00:02:53,000 In the on the x axis x axis, you can see a latency. 39 00:02:53,000 --> 00:02:58,000 Latency is basically a time that is taken to do object detection on an input image. 40 00:02:58,000 --> 00:03:07,000 So from the graph we can clearly see that Yolo YOLO 11 takes less inference time and it is more accurate 41 00:03:07,000 --> 00:03:10,000 as compared to other YOLO models. 42 00:03:11,000 --> 00:03:17,000 So you might be thinking how we can use YOLO 11 to perform object detection, instance segmentation 43 00:03:17,000 --> 00:03:23,000 and pose estimation to use yellow 11 to perform object detection, instance segmentation, and pose 44 00:03:23,000 --> 00:03:24,000 estimation. 45 00:03:24,000 --> 00:03:27,000 You just need to install the Ultralytics package and nothing more. 46 00:03:27,000 --> 00:03:33,000 You just need to install Ultralytics package by writing pip install Ultralytics, and you can also use 47 00:03:33,000 --> 00:03:38,000 your 11 directly into your command line interface using the YOLO command. 48 00:03:38,000 --> 00:03:43,000 And so you can simply write YOLO and predict mode, and you can just model in the model. 49 00:03:43,000 --> 00:03:47,000 You can just pass the name of the YOLO 11 model you want to use. 50 00:03:47,000 --> 00:03:53,000 User 11 comes with five different models, and 11 nano is the smallest and it is the most fast, but 51 00:03:53,000 --> 00:03:54,000 it is less accurate. 52 00:03:54,000 --> 00:03:57,000 While user 11 Extra Large is the most accurate. 53 00:03:57,000 --> 00:04:01,000 But it takes more inference time as compared to other YOLO models. 54 00:04:01,000 --> 00:04:06,000 So you can use any of the YOLO 11 model as per your requirements and in the source you can pass your 55 00:04:06,000 --> 00:04:09,000 input image, video or live feed path. 56 00:04:09,000 --> 00:04:15,000 So in this way you can uh, you can do object detection, instance segmentation, and pose estimation 57 00:04:15,000 --> 00:04:19,000 using YOLO 11 by writing these two lines of code. 58 00:04:19,000 --> 00:04:21,000 So that's all from this tutorial. 59 00:04:21,000 --> 00:04:24,000 And I have given you a quick demo about YOLO 11. 60 00:04:24,000 --> 00:04:26,000 So let's get started with this.