Energy consumption is a crucial issue of mobile surveillance cameras owing to limited battery capacity. The lifetime of the system is significantly extended by the eventdriven operation; the system mostly stays in sleep mode and wakes up only when an event is detected. In this paper, we propose a design of a low-energy surveillance camera that records events such as the abnormal movement of objects, or physical damage to the camera itself. Unlike conventional event-driven approaches, the proposed system records video from 10 seconds before the event detection because the most critical information is often before or at the moment of event detection, not after the detection. Two different encoders, a low-power encoder and a highcompression encoder, are employed together to implement the low-energy surveillance camera. Experimental results show that the energy consumption of the whole system is reduced by up to 74.9% (by 66.8% on average) compared with conventional always-on system.
Blown films based on low-density polyethylene (LDPE)/linear low-density polyethylene (LLDPE) and silica aerogel (SA; 0, 0.5, 1, and 1.5 wt.%) were obtained at the pilot scale. Good particle dispersion and distribution were achieved without thermo oxidative degradation. The effects of different SA contents (0.5–1.5 wt.%) were studied to prepare transparent-heat-retention LDPE/LLDPE films with improved material properties, while maintaining the optical performance. The optical characteristics of the composite films were analyzed using methods such as ultraviolet–visible spectroscopy and electron microscopy. Their mechanical characteristics were examined along the machine and transverse directions (MD and TD, respectively). The MD film performance was better, and the 0.5% composition exhibited the highest stress at break. The crystallization kinetics of the LDPE/LLDPE blends and their composites containing different SA loadings were investigated using differential scanning calorimetry, which revealed that the crystallinity of LDPE/LLDPE was increased by 0.5 wt.% of well-dispersed SA acting as a nucleating agent and decreased by agglomerated SA (1–1.5 wt.%). The LDPE/LLDPE/SA (0.5–1.5 wt.%) films exhibited improved infrared retention without compromising the visible light transmission, proving the potential of this method for producing next-generation heat retention films. Moreover, these films were biaxially drawn at 13.72 MPa, and the introduction of SA resulted in lower draw ratios in both the MD and TD. Most of the results were explained in terms of changes in the biaxial crystallization caused by the process or the influence of particles on the process after a systematic experimental investigation. The issues were strongly related to the development of blown nanocomposites films as materials for the packaging industry.
Advances in deep neural networks (DNNs) have led to impressive results and in recent years many works have exploited DNNs for anomaly detection. Among others, generative/reconstruction modelbased methods have been frequently used for anomaly detection because they do not require any labels for training. The anomaly detection performance of these methods, however, varies a lot, due to the change of the intra-class variance and the difference in complexity of input samples. In addition, most previous state-of-the-art works on anomaly detection have empirically adjusted several hyperparameters to heighten their performance of anomaly detection. These sorts of procedures are known to be impractical and create obstacles in real world anomaly detection. To solve these problems, we propose a hybrid discriminator with a correlative autoencoder for anomaly detection. In the proposed framework, the discriminator implicitly estimates the conditional probability density function and the autoencoder has improved ability to control the reconstruction error. We provide theoretical foundation of our method and verify it through various experiments. We also confirm practical benefits of our interpretation of the conditional expectation and the proposed framework by comparing our results with other state-of-the-art methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.