Search

Abstract The Wi‐Fi‐based human activity recognition shows immense potential, as it is device‐free, non‐intrusive to privacy, and low‐cost. However, current learning‐based recognition methods mostly adopt the hybrid representation without distinguished contributions of features to different activities, which will be seriously affected by environment variations and interference of other persons, and costly to extend to new activities. Therefore, this paper proposes HR‐HAR, a hierarchical relation representation for human activity recognition, to improve the performance, extensibility, and robustness by exploiting the hierarchical relation of features of activities. The hierarchical relation reflects the different contributions of features to recognize different activities and effectively distinguishes similar activities. It naturally leads to a layered structure that can be extended to new activities without re‐training the entire model. With the layered structure, HR‐HAR first detects the existence of other persons and then processes un‐interfered scene and interfered scene signals with different methods, so it is robust to the interference. The experimental results on the public dataset with 95.6% accuracy and on the self‐collected dataset with 95.4% accuracy for un‐interfered scene and 95.0% for interfered scene indicate that HR‐HAR is of reliable performance on human activity recognition and is robust to environmental changes and interference of other persons.

Person re-identification has become a challenging task due to various factors. One key to effective person re-identification is the extraction of the discriminative features of a person's appearance. Most previous works based on deep learning extract pedestrian characteristics from neural networks but only from the top feature layer. However, the low-layer feature could be more discriminative in certain circumstances. Hence, we propose a method, named the multi-level feature network with multiple losses (MFML), which has a multi-branch network architecture that consists of multiple middle layers and one top layer for feature representations. To extract the discriminative middle-layer features and have a good effect on deeper layers, we utilize the triplet loss function to train the middle-layer features. For the top layer, we focus on learning more discriminative feature representations, so we utilize the hybrid loss (HL) function to train the top-layer feature. Instead of concatenating multilayer features directly, we concatenate the weighted middle-layer features and the weighted top-layer feature as the discriminative features in the testing phase. The extensive evaluations conducted on three datasets show that our method achieves a competitive accuracy level compared with the state-of-the-art methods.

Visibility of outdoor scenes is often degraded by haze. The atmosphere particles absorb and scatter the light, causing failure in various computer vision applications. In this paper, we propose a naturalness preserved fast dehazing algorithm using hue, saturation, and value (HSV) color space. First, we process hazy images in HSV color space instead of red, green, and blue (RBG) in order to preserve hue and reduce computational complexity. Second, we use the modified morphological opening operation for estimating the transmission map. In this way, the halo effects are greatly suppressed, and it costs less time than the specially designed filters. The experimental results demonstrate that the proposed algorithm can effectively remove haze. Also, our algorithm maintains naturalness by preserving hue and suppressing halo effects. Moreover, the computational complexity has been largely reduced, thus making our algorithm appropriate for real-time applications.

The pedestrian attribute recognition aims to generate a structured description of pedestrians, which serves an important role in surveillance. Current works usually assume that the images and the specific pedestrian states, including pedestrian occlusion and pedestrian orientation, are given. However, we argue that the current works ignore the guidance of the pedestrian state and cannot achieve the appropriate performance since the appearance feature will become unreliable due to the variance of the pedestrian state, which is common in practice. Therefore, this paper proposes the Explicit State Representation (ExSR) Guided Pedestrian Attribute Recognition to improve the accuracy through state learning and attribute fusion among frames. Firstly, the pedestrian state is explicitly represented by concatenating the pedestrian orientation and occlusion, which can be accurately determined via analyzing the pose. Secondly, the state-aware pedestrian attribute fusion method is proposed and divided into two cases, namely the inter-state case and the intra-state case. In the intra-state case, the appearance feature will remain stable and the attribute relations are propagated to refine. The method of exploiting attribute relations within a single frame is the Graph Neural Network. In the inter-state case, the state changes, the attribute relationship propagation is prevented, and the advantages of attribute recognition in each frame are complemented to make a reliable judgment on the invisible region. The experimental results demonstrate that the ExSR outperforms the state-of-the-art methods on two public databases, benefiting from the explicit introduction of the state into the attribute recognition. [ABSTRACT FROM AUTHOR]

Real-time learning on real-world data streams with temporal relations is essential for intelligent agents. However, current online Continual Learning (CL) benchmarks adopt the mini-batch setting and are composed of temporally unrelated and disjoint tasks aswell as pre-set class boundaries. In this paper,we delve into a realworld CL scenario for fresh recognition where algorithms are required to recognize a huge variety of products to facilitate the checkout speed. Products mainly consists of packaged cereals, seasonal fruits, and vegetables from local farms or shipped from overseas. Since algorithms process instance streams consisting of sequential images, we name this real-world CL problem as Instance-Based Continual Learning (IBCL). Different from the current online CL setting, algorithms are required to perform instant testing and learning upon each incoming instance. Moreover, IBCL has no task boundaries or class boundaries and allows the evolution and the forgetting of old samples within each class. To promote the researches on real CL challenges, we propose the first real-world CL dataset coined the Continual Fresh Recognition (CFR) dataset, which consists of fresh recognition data streams (766K labelled images in total) collected from 30 supermarkets. Based on the CFR dataset, we extensively evaluate the performance of current online CL methods under various settings and find that current prominent online CL methods operate at high latency and demand significant memory consumption to cache old samples for replaying. Therefore, we make the first attempt to design an efficient and effective Instant Training-Free Learning (ITFL) framework for IBCL. ITFL consists of feature extractors trained in the metric learning manner and reformulates CL as a temporal classification problem among several most similar classes. Unlike current online CL methods that cache image samples (150KB per image) and rely on training to learn new knowledge, our framework only caches features (2KB per image) and is free of training in deployment. Extensive evaluations across three datasets demonstrate that our method achieves comparable recognition accuracy to current methods with lower latency and less resource consumption. Our codes and datasets will be publicly available at https://github.com/detectRecog/IBCL. [ABSTRACT FROM AUTHOR]

This paper presents a method for the combination of different feature cues in a level set based moving object segmentation framework. To distinguish object from background, motion detection is firstly adopted to locate object position and obtain coarse shape prior. Moreover, the color and texture feature descriptors that represent object contour are designed in this dissertation. Then the finer segmentation solution based on the color and texture difference between the object and background is proposed, which avoids the invalid feature components to hamper segmentation and improves the accuracy. Extensive experiments have been carried out on surveillance video sequences to validate the proposed method. [ABSTRACT FROM AUTHOR]

Rate control plays an important role in video coding. However, in the conventional rate control algorithms, the number and position of macroblocks (MBs) inside one basic unit for rate control is inflexible and predetermined. The different characteristics of the MBs are not fully considered. Also, there is no overall optimization of the coding of basic units. This paper proposes a new region-based rate control scheme for H.264/advanced video coding to improve the coding efficiency. The inter-frame information is explored to objectively divide one frame into multiple regions based on their rate-distortion (R-D) behaviors. The MBs with similar characteristics are classified into the same region, and the entire region, instead of a single MB or a group of contiguous MBs, is treated as a basic unit for rate control. A linear rate-quantization stepsize model and a linear distortion-quantization stepsize model are proposed to accurately describe the R-D characteristics for the region-based basic units. Moreover, based on the above linear models, an overall optimization model is proposed to obtain suitable quantization parameters for the region-based basic units. Experimental results demonstrate that the proposed region-based rate control approach can achieve both better subjective and objective quality by performing the rate control adaptively with the content, compared to the conventional rate control approaches. [ABSTRACT FROM AUTHOR]