Interactive Attention Learning on Detection of Lane and Lane Marking on the Road by Monocular Camera Image.

Vision-based identification of lane area and lane marking on the road is an indispensable function for intelligent driving vehicles, especially for localization, mapping and planning tasks. However, due to the increasing complexity of traffic scenes, such as occlusion and discontinuity, detecting lanes and lane markings from an image captured by a monocular camera becomes persistently challenging. The lanes and lane markings have a strong position correlation and are constrained by a spatial geometry prior to the driving scene. Most existing studies only explore a single task, i.e., either lane marking or lane detection, and do not consider the inherent connection or exploit the modeling of this kind of relationship between both elements to improve the detection performance of both tasks. In this paper, we establish a novel multi-task encoder-decoder framework for the simultaneous detection of lanes and lane markings. This approach deploys a dual-branch architecture to extract image information from different scales. By revealing the spatial constraints between lanes and lane markings, we propose an interactive attention learning for their feature information, which involves a Deformable Feature Fusion module for feature encoding, a Cross-Context module as information decoder, a Cross-IoU loss and a Focal-style loss weighting for robust training. Without bells and whistles, our method achieves state-of-the-art results on tasks of lane marking detection (with 32.53% on IoU, 81.61% on accuracy) and lane segmentation (with 91.72% on mIoU) of the BDD100K dataset, which showcases an improvement of 6.33% on IoU, 11.11% on accuracy in lane marking detection and 0.22% on mIoU in lane detection compared to the previous methods.

A novel microRNA, novel-m009C, regulates methamphetamine rewarding effects.

Methamphetamine (METH) is a widely abused psychostimulant, whose hyper-rewarding property is believed to underlie its addictive effect, but the molecular mechanism regulating this effect remains unclear. We previously reported that decreased expression of a novel microRNA (miRNA), novel-m009C, is implicated in the regulation of METH hyperlocomotion. Here, we found that novel-m009C may be homologous to hsa-miR-604. Its expression is consistently downregulated in the nucleus accumbens (NAc) of mice when exposed to METH and cocaine, whereas significant alterations in novel-m009C expression were not observed in the NAc of mice subjected to other rewarding and psychiatric stimuli, such as sucrose, morphine and MK-801. We further found the substantial reduction in novel-m009C expression may be regulated by both dopamine receptor D1 (D1R) and D2 (D2R). Increasing novel-m009C levels in the NAc attenuated METH-induced conditioned place preference (CPP) and hyperlocomotion, whereas inhibiting novel-m009C expression in the NAc enhanced these effects but did not change the preference of mice for a natural reward, i.e., sucrose. These effects may involve targeting of genes important for the synaptic transmission, such as Grin1 (NMDAR subunit 1). Our findings demonstrate an important role for NAc novel-m009C in regulating METH reward, reveal a novel molecular regulator of the actions of METH on brain reward circuitries and provide a new strategy for treating METH addiction based on the modulation of small non-coding RNAs.

Sugar Beverage Habitation Relieves Chronic Stress-Induced Anxiety-like Behavior but Elicits Compulsive Eating Phenotype via vLSGAD2 Neurons.

Chronically stressed individuals are reported to overconsume tasty, palatable foods like sucrose to blunt the psychological and physiological impacts of stress. Negative consequences of high-sugar intake on feeding behavior include increased metabolic disease burdens like obesity. However, the neural basis underlying long-term high-sugar intake-induced overeating during stress is not fully understood. To investigate this question, we used the two-bottle sucrose choice paradigm in mice exposed to chronic unpredictable mild stressors (CUMS) that mimic those of daily life stressors. After 21 days of CUMS paralleled by consecutive sucrose drinking, we explored anxiety-like behavior using the elevated plus maze and open field tests. The normal water-drinking stressed mice displayed more anxiety than the sucrose-drinking stressed mice. Although sucrose-drinking displayed anxiolytic effects, the sucrose-drinking mice exhibited binge eating (chow) and a compulsive eating phenotype. The sucrose-drinking mice also showed a significant body-weight gain compared to the water-drinking control mice during stress. We further found that c-Fos expression was significantly increased in the ventral part of the lateral septum (vLS) of the sucrose-treated stressed mice after compulsive eating. Pharmacogenetic activation of the vLS glutamate decarboxylase 2(GAD2) neurons maintained plain chow intake but induced a compulsive eating phenotype in the naïve GAD2-Cre mice when mice feeding was challenged by flash stimulus, mimicking the negative consequences of excessive sucrose drinking during chronic stress. Further, pharmacogenetic activation of the vLSGAD2 neurons aggravated anxiety of the stressed GAD2-Cre mice but did not alter the basal anxiety level of the naïve ones. These findings indicate the GABAergic neurons within the vLS may be a potential intervention target for anxiety comorbid eating disorders during stress.

Continuous Fusion of Motion Data Using an Axis-Angle Rotation Representation with Uniform B-Spline.

The fusion of motion data is key in the fields of robotic and automated driving. Most existing approaches are filter-based or pose-graph-based. By using filter-based approaches, parameters should be set very carefully and the motion data can usually only be fused in a time forward direction. Pose-graph-based approaches can fuse data in time forward and backward directions. However, pre-integration is needed by applying measurements from inertial measurement units. Additionally, both approaches only provide discrete fusion results. In this work, we address this problem and present a uniform B-spline-based continuous fusion approach, which can fuse motion measurements from an inertial measurement unit and pose data from other localization systems robustly, accurately and efficiently. In our continuous fusion approach, an axis-angle is applied as our rotation representation method and uniform B-spline as the back-end optimization base. Evaluation results performed on the real world data show that our approach provides accurate, robust and continuous fusion results, which again supports our continuous fusion concept.

Research Progress and Development Trends of Acoustic Metamaterials.

Acoustic metamaterials are materials with artificially designed structures, which have characteristics that surpass the behavior of natural materials, such as negative refraction, anomalous Doppler effect, plane focusing, etc. This article mainly introduces and summarizes the related research progress of acoustic metamaterials in the past two decades, focusing on meta-atomic acoustic metamaterials, metamolecular acoustic metamaterials, meta-atomic clusters and metamolecule cluster acoustic metamaterials. Finally, the research overview and development trend of acoustic metasurfaces are briefly introduced.

Stimulation of bioluminescence in Noctiluca sp. using controlled temperature changes.

Bioluminescence induced by multifarious stimuli has long been observed and is remains under investigation because of its great complexity. In particular, the exact mechanism underlying bioluminescence is not yet fully understood. This work presents a new experimental method for studying Noctiluca sp. bioluminescence under temperature change stimulation. It is a study of Noctiluca sp. bioluminescence using controlled temperature changes in a tank. A characteristic of this experiment is the large volume of water used (1 m(3) in a tank of 2 × 1 × 1 m). Temperature changes were controlled by two methods. In the first, a flask filled with hot water was introduced into the tank and in the second, a water heater was used in the tank. Temperature changes were recorded using sensors. Noctiluca sp. bioluminescence was recorded using a Canon 5D Mark II and this allowed the characteristics of Noctiluca sp. bioluminescence under temperature change stimulation to be monitored.