ABSTRACT
Smart security based on object detection is one of the important applications of edge computing in IoT. Anchors in object detection refer to points on the feature map, which can be used to generate anchor boxes and serve as training samples. Current object detection models do not consider the aspect ratio of the ground-truth boxes in anchor assignment and are not well-adapted to objects with very different shapes. Therefore, this paper proposes the Lightweight Anchor Dynamic Assignment algorithm (LADA) for object detection. LADA does not change the structure of the original detection model; first, it selects an equal proportional center region based on the aspect ratio of the ground-truth box, then calculates the combined loss of anchors, and finally divides the positive and negative samples more efficiently by dynamic loss threshold without additional models. The algorithm solves the problems of poor adaptability and difficulty in the selection of the best positive samples based on IoU assignment, and the sample assignment for eccentric objects and objects with different aspect ratios was more reasonable. Compared with existing sample assignment algorithms, the LADA algorithm outperforms the MS COCO dataset by 1.66% over the AP of the baseline FCOS, and 0.76% and 0.24% over the AP of the ATSS algorithm and the PAA algorithm, respectively, with the same model structure, which demonstrates the effectiveness of the LADA algorithm.
ABSTRACT
Human parsing is an important technology in human-robot interaction systems. At present, the distribution of multi-category human parsing datasets is unbalanced, and the samples present a long-tailed distribution, which directly affects the performance of human parsing. Meanwhile, the similarity between different categories leads the model to predict false parsing results. To solve the above problems, a general decoupled training framework called Decoupled Training framework based on Pixel Resampling (DTPR) was proposed to solve the long-tailed distribution, and a new sampling method named Pixel Resampling based on Accuracy distribution (PRA) for semantic segmentation was also proposed and applied to this decoupled training framework. The framework divides the training process into two phases, the first phase is to improve the model feature extraction ability, and the second phase is to improve the performance of the model on tail categories. The training framework was evaluated in MHPv2.0 and LIP datasets, and tested in both high-precision and real-time SOTA models. The MPA metric of model trained by DTPR in above two datasets increased by more than 6%, and the mIoU metric increased by more than 1% without changing the model structure.
Subject(s)
Algorithms , HumansABSTRACT
In order to accelerate the transformation of offline retailers and improve sales by using big data technology, this paper proposes a data-driven customer profile modeling method based on the collected historical purchase records of offline consumers. This method is mainly divided into three aspects: (1) an incremental RFM model is designed to classify the value of historical consumers and support the dynamic update of the model, which is more efficient than the traditional RFM model; (2) the commodity preference of different types of customers is analyzed by the TGI model, so as to guide the retail terminal to optimize the marketing strategy; (3) a commodity purchase behavior prediction model based on LSTM is proposed, which can predict the commodity that each customer may purchase in the future, so as to optimize the retail strategy. According to extensive experiments based on a true tobacco dataset, the incremental RFM model can save 80% more time than the traditional method, and our proposed prediction model can achieve 59.32% accuracy, which is better than other baselines.
