Noise causes unpleasant visual effects in low-light image/video enhancement. In this paper, we aim to make the enhancement model and method aware of noise in the whole process. To deal with heavy ...noise which is not handled in previous methods, we introduce a robust low-light enhancement approach, aiming at well enhancing low-light images/videos and suppressing intensive noise jointly. Our method is based on the proposed Low-Rank Regularized Retinex Model (LR3M), which is the first to inject low-rank prior into a Retinex decomposition process to suppress noise in the reflectance map. Our method estimates a piece-wise smoothed illumination and a noise-suppressed reflectance sequentially, avoiding remaining noise in the illumination and reflectance maps which are usually presented in alternative decomposition methods. After getting the estimated illumination and reflectance, we adjust the illumination layer and generate our enhancement result. Furthermore, we apply our LR3M to video low-light enhancement. We consider inter-frame coherence of illumination maps and find similar patches through reflectance maps of successive frames to form the low-rank prior to make use of temporal correspondence. Our method performs well for a wide variety of images and videos, and achieves better quality both in enhancing and denoising, compared with the state-of-the-art methods.
Many low-light enhancement methods ignore intensive noise in original images. As a result, they often simultaneously enhance the noise as well. Furthermore, extra denoising procedures adopted by most ...methods ruin the details. In this paper, we introduce a joint low-light enhancement and denoising strategy, aimed at obtaining well-enhanced low-light images while getting rid of the inherent noise issue simultaneously. The proposed method performs Retinex model based decomposition in a successive sequence, which sequentially estimates a piece-wise smoothed illumination and a noise-suppressed reflectance. After getting the illumination and reflectance map, we adjust the illumination layer and generate our enhancement result. In this noise-suppressed sequential decomposition process we enforce the spatial smoothness on each component and skillfully make use of weight matrices to suppress the noise and improve the contrast. Results of extensive experiments demonstrate the effectiveness and practicability of our method. It performs well for a wide variety of images, and achieves better or comparable quality compared with the state-of-the-art methods.
Participants in a conversation must carefully monitor the turn-management (speaking and listening) willingness of other conversational partners and adjust their turn-changing behaviors accordingly to ...have smooth conversation. Many studies have focused on developing actual turn-changing (i.e., next speaker or end-of-turn) models that can predict whether turn-keeping or turn-changing will occur. Participants' verbal and non-verbal behaviors have been used as input features for predictive models. To the best of our knowledge, these studies only model the relationship between participant behavior and turn-changing. Thus, there is no model that takes into account participants' willingness to acquire a turn (turn-management willingness). In this paper, we address the challenge of building such models to predict the willingness of both speakers and listeners. Firstly, we find that dissonance exists between willingness and actual turn-changing. Secondly, we propose predictive models that are based on trimodal inputs, including acoustic, linguistic, and visual cues distilled from conversations. Additionally, we study the impact of modeling willingness to help improve the task of turn-changing prediction. To do so, we introduce a dyadic conversation corpus with annotated scores of speaker/listener turn-management willingness. Our results show that using all three modalities (i.e., acoustic, linguistic, and visual cues) of the speaker and listener is critically important for predicting turn-management willingness. Furthermore, explicitly adding willingness as a prediction task improves the performance of turn-changing prediction. Moreover, turn-management willingness prediction becomes more accurate when this joint prediction of turn-management willingness and turn-changing is performed by using multi-task learning techniques.
This study aimed to achieve a clear understanding of the response characteristics of soft pack battery extrusion conditions under various situations. In this study, we chose a LiCoO2 battery as the ...research object of the extrusion experiment. First, the repeatability of the extrusion test on the battery was verified. A quasi-static extrusion test was conducted on three groups of batteries in the same state, and the load-displacement curves of the three groups of experimental batteries were almost the same. Then, the influence of the extrusion speed on the battery thermal runaway was studied. The results show that a different extrusion speed has a certain impact on the thermal runaway performance of the battery. The peak load of the battery is lower at a lower speed. Finally, the study found that every 20% change in SOC has a greater impact on the battery response under a squeeze. The larger the SOC, the more severe the battery thermal runaway. Through an analysis of multiple experimental cases, it is possible to have a deeper understanding of the temperature and voltage characteristics of lithium batteries when a thermal runaway occurs, which provides ideas for monitoring the trend of the thermal runaway of electric vehicles.
An efficient and safe thermal insulation structure design is critical in battery thermal management systems to prevent thermal runaway propagation. In this paper, using a common real-life overcharge ...as a trigger for battery runaway, we investigate the runaway response of the battery module without thermal insulation and with various thermal insulation materials. The experimental results indicate that the thermal insulation has the effect of stopping the thermal spread of the battery module and reducing the maximum temperature. By comparing the temperature change of the batteries, it is discovered that the fiber-based material has a temperature drop efficiency of 71.83%, while the aerogel materials are at least 13% more efficient in temperature reduction than fibrous materials. Meanwhile, it is demonstrated that by examining the capacity characteristics of the damaged battery and the characteristics of the insulation material, the pre-oxidized silk aerogel has the best thermal spread suppression effect and the TG (thermogravimetric) variation withstood high temperatures of up to 746 °C. SEM (scanning electron microscope) morphology for different insulation materials before and after combustion show that pre-oxidized silk aerogel maintains a strong thermal insulation capacity in the thermal spreading. It is expected to have a guidance for the design of thermal insulation in lithium-ion battery modules.
•The greater the overcharge multiplier, the higher the temperature following thermal runaway.•The battery is highly susceptible to TR when the surface temperature exceed 200 °C.•The fiber material have a temperature drop efficiency of 71.83%.•The aerogel materials are at least 13% in temperature reduction than fibrous materials.•The pre-oxidized silk aerogel have the best thermal spread suppression effect.
Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, ...for which we solve so-called jigsaw puzzles, i.e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration. Existing approaches formulated it as a classification task by defining a fixed mapping from a small subset of configurations to a class set, but these approaches ignore the underlying relationship between different configurations and also limit their applications to more complex scenarios. This paper presents a novel approach which applies to jigsaw puzzles with an arbitrary grid size and dimensionality. We provide a fundamental and generalized principle, that weaker cues are easier to be learned in an unsupervised manner and also transfer better. In the context of puzzle recognition, we use an iterative manner which, instead of solving the puzzle all at once, adjusts the order of the patches in each step until convergence. In each step, we combine both unary and binary features of each patch into a cost function judging the correctness of the current configuration. Our approach, by taking similarity between puzzles into consideration, enjoys a more efficient way of learning visual knowledge. We verify the effectiveness of our approach from two aspects. First, it solves arbitrarily complex puzzles, including high-dimensional puzzles, that prior methods are difficult to handle. Second, it serves as a reliable way of network initialization, which leads to better transfer performance in visual recognition tasks including classification, detection and segmentation.
The equivalent circuit model (ECM) is a type of lithium-ion battery model that is widely used in electric vehicle battery management systems (BMS). BMS is an important component that affects the ...performance of electric vehicles, and accurate battery model is the foundation of BMS. For different usage scenarios, improving the accuracy of battery model in BMS plays a crucial role in improving the energy utilization of electric vehicles and ensuring the safe use of batteries. The accuracy of the battery model is strongly influenced by the accuracy of the battery model parameters, therefore, this study aimed at elucidating on these factors. In this paper, experimental procedures for model parameter identification are designed and optimized by orthogonal analysis in terms of model accuracy, model consistency, and maximum model error. Model parameters that can synthetically balance the three model evaluation indices are finally obtained through experiments. By combining the obtained experimental contents and analysis results, we quantitatively investigated the sensitivity of different model performances to the three model parameters in ECM under different state of charge (SOC) using a combination of polynomial fitting and derivative solving sensitivity by single-factor sensitivity analysis. This study provides a basis for future battery modeling, model error analysis, and model parameter identification. In addition, we propose the optimization parameter as an indicator for optimizing the parameters in the battery model in conjunction with parameter sensitivity to model performance and degree of deviation from standard model parameters. The validation shows that the optimized battery model parameters using this method can improve the model's specific performance.
•OCV-SOC curves are fitted using cubic spline interpolation.•ECM of 1-order RC is studied from three perspectives: accuracy, consistency, and maximum error.•A better HPPC test protocol is obtained by orthogonal experimental analysis.•The sensitivity of the battery model performance to the parameters was investigated separately.•The ECM is optimized by combining the optimization parameters proposed by the parameter sensitivity.
The rapid development of new energy vehicles has drawn widespread attention to battery safety. Overcharging, as an important source of thermal runaway, may occur instantaneously without obvious ...signs, and any corresponding fire will be difficult to extinguish. This study is an investigation of overcharging thermal runaway and thermal runaway warnings for lithium-ion batteries. A stress-type early warning system is proposed, which has faster response time and more distinctive characteristics compared with other parameters. Through the association rule mining method, a multi-parameter coupled thermal runaway early warning strategy based on voltage, temperature, and pressure parameters was designed. A hierarchical early warning model including feature extraction, data processing and early warning evaluation modules was established. On this basis, a remaining time prediction module was added to achieve an alarm escape time of up to 474 s and shortest of 65 s, meeting safety standards. In the thermal runaway experiment at 705.2 °C, the early warning level system was triggered respectively. The maximum battery temperatures were 28.4 °C, 41.5°Cand 60.3 °C. The escape time errors were 16.56 s, 11.52 s, and 11.88 s respectively, all within 20 s for each level. Corresponding to different experimental results, the significant level classification simultaneously verifies the accuracy and effectiveness of the classification strategy.
•A multiparameter coupling thermal runaway early warning strategy•Quick response pressure•Hierarchical warning model
For smooth conversation, participants must carefully monitor the turn-management (a.k.a. speaking and listening) willingness of other conversational partners and adjust turn-changing behaviors ...accordingly. Many studies have focused on predicting the actual moments of speaker changes (a.k.a. turn-changing), but to the best of our knowledge, none of them explicitly modeled the turn-management willingness from both speakers and listeners in dyad interactions. We address the problem of building models for predicting this willingness of both. Our models are based on trimodal inputs, including acoustic, linguistic, and visual cues from conversations. We also study the impact of modeling willingness to help improve the task of turn-changing prediction. We introduce a dyadic conversation corpus with annotated scores of speaker/listener turn-management willingness. Our results show that using all of three modalities of speaker and listener is important for predicting turn-management willingness. Furthermore, explicitly adding willingness as a prediction task improves the performance of turn-changing prediction. Also, turn-management willingness prediction becomes more accurate with this multi-task learning approach.
The listener's backchannel has the important function of encouraging a current speaker to hold their turn and continue to speak, which enables smooth conversation. The listener monitors the speaker's ...turn-management (a.k.a. speaking and listening) willingness and his/her own willingness to display backchannel behavior. Many studies have focused on predicting the appropriate timing of the backchannel so that conversational agents can display backchannel behavior in response to a user who is speaking. To the best of our knowledge, none of them added the prediction of turn-changing and participants' turn-management willingness to the backchannel prediction model in dyad interactions. In this paper, we proposed a novel backchannel prediction model that can jointly predict turn-changing and turn-management willingness. We investigated the impact of modeling turn-changing and willingness to improve backchannel prediction. Our proposed model is based on trimodal inputs, that is, acoustic, linguistic, and visual cues from conversations. Our results suggest that adding turn-management willingness as a prediction task improves the performance of backchannel prediction within the multi-modal multi-task learning approach, while adding turn-changing prediction is not useful for improving the performance of backchannel prediction.