Handbook of Intelligent Computing and Optimization for Sustainable Development. Группа авторов. Читать онлайн. Newlib. NEWLIB.NET

Автор: Группа авторов
Издательство: John Wiley & Sons Limited
Серия:
Жанр произведения: Техническая литература
Год издания: 0
isbn: 9781119792628
Скачать книгу
that is close to the wrists of a customer. This indicates that the customer in consideration is interested in the given active garment. We determine this by establishing a Confidence Score (C) between a person’s wrists and an active garment.

       3.3.3.1 Centroid Tracking

      A person detected by the Mask R-CNN [9] in Stage 1 is tracked by leveraging the Centroid-based tracking algorithm proposed by Nascimento et al. [20]. This algorithm tracks the identified persons by measuring the Euclidean distance between the centroids of people detected over successive frames. It works based on the presumption that even though an object will move between the resulting frames of a recording, the distance between the centroid of the same object between two consecutive frames will be less than the distance to the centroid of some other object identified in the given frames.

      This step enables us to track and associate every person detected in the recording with a unique tracking ID across numerous frames.

       3.3.3.2 Pose Estimation

      We determine the coordinates of a person’s wrists using a state-of-the-art pose estimation framework, OpenPose [10]. OpenPose is the first real-time 2D multi-person human pose estimation framework that achieves the tasks of jointly detecting the human body, hand, face, and foot-related key points from a single image. The OpenPose framework identifies a total of 135 feature points in the detected human. This is accomplished using a multi-stage Convolutional Neural Network (CNN) that uses a nonparametric representation called Part Affinity Fields (PAFs) to learn how to associate the body parts with the corresponding humans in the image. The OpenPose multi-stage CNN architecture has three crucial steps:

      1 1. The first set of stages predicts the PAFs from the input feature map.

      2 2. The second set of stages utilizes the PAFs from the previous layers to refine the prediction of confidence maps detection.

      3 3. The final set of detected PAFs and Confidence Maps are passed into a greedy algorithm, which approximates the global solution, by displaying the various key points in the given input image.

      The architecture of the CNN used in OpenPose consists of a convolution step that utilizes two consecutive 3×3 convolutional kernels. The convolution is performed in order to reduce the number of computations. Additionally, the output of each of the aforementioned convolutional kernels is concatenated, producing the basic convolution step in the multistage CNN. Before passing the input image (in RGB color space) to the first stage of the network, the image is passed through the first 10 layers of the VGG-19 network to generate a set of feature maps. These feature maps are then passed through the multi-stage CNN pipeline to generate Part Confidence Maps and PAF. A confidence map is a 2D representation of the belief that a given body part can be located in a given pixel of the input image. PAF is a set of 2D vector fields that encodes the orientation and the location of body parts in a given image.

Schematic illustration of the key points for pose output.

      The confidence score (C) is calculated for each pair-wise distinct set of detected person’s wrists and active garment where the highest score is retained for that active garment. If this confidence score exceeds a specified confidence threshold (δ), then the active garment in consideration is considered to be a garment of interest to the given customer as his/her wrist landmarks are in close proximity with the garment. The proposed approach also notes the time duration for which such interaction takes place by keeping track of the number of frames for which the active garment is a garment of interest for the given customer.

      3.4.1 Dataset Used