This paper presents an effective nighttime vehicle detection system that combines a novel bioinspired image enhancement approach with a weighted feature fusion technique. Inspired by the retinal mechanism in natural visual processing, we develop a nighttime image enhancement method by modeling the adaptive feedback from horizontal cells and the center-surround antagonistic receptive fields of bipolar cells. Furthermore, we extract features based on the convolutional neural network, histogram of oriented gradient, and local binary pattern to train the classifiers with support vector machine. These features are fused by combining the score vectors of each feature with the learnt weights. During detection, we generate accurate regions of interest by combining vehicle taillight detection with object proposals. Experimental results demonstrate that the proposed bioinspired image enhancement method contributes well to vehicle detection. Our vehicle detection method demonstrates a 95.95% detection rate at 0.0575 false positives per image and outperforms some state-of-the-art techniques. Our proposed method can deal with various scenes including vehicles of different types and sizes and those with occlusions and in blurred zones. It can also detect vehicles at various locations and multiple vehicles.

Night-time vehicle detection is essential in building intelligent transportation systems (ITS) for road safety. Most of current night-time vehicle detection approaches focus on one or two classes of vehicles. In this paper, we present a novel multiclass vehicle detection system based on tensor decomposition and object proposal. Commonly used features such as histogram of oriented gradients and local binary pattern often produce useless image blocks (regions), which can result in unsatisfactory detection performance. Thus, we select blocks via feature ranking after tensor decomposition and only extract features from these selected blocks. To generate windows that contain all vehicles, we propose a novel object-proposal approach based on a state-of-the-art object-proposal method, local features, and image region similarity. The three terms are summed with learned weights to compute the reliability score of each proposal. A bio-inspired image enhancement method is used to enhance the brightness and contrast of input images. We have built a Hong Kong night-time multiclass vehicle dataset for evaluation. Our proposed vehicle detection approach can successfully detect four types of vehicles: 1) car; 2) taxi; 3) bus; and 4) minibus. Occluded vehicles and vehicles in the rain can also be detected. Our proposed method obtains 95.82% detection rate at 0.05 false positives per image, and it outperforms several state-of-the-art night-time vehicle detection approaches.

Object proposal is one of the most key pre-processing steps for nighttime vehicle detection systems in intelligent transportation systems. However, most current object proposal methods are developed on daytime data sets, and these methods demonstrate unsatisfactory results when they are used on nighttime images. Therefore, this paper presents a novel Bayes saliency-based object proposal generator for nighttime RGB traffic images to generate a modest and accurate set of proposals, which are more likely to be vehicles for preceding vehicle detection. First, we propose a new Bayes saliency detection approach in which prior estimation, feature extraction, weight estimation, and Bayes rule are used to compute saliency maps. Then, we propose a simple but effective object proposal generator based on the Bayes saliency map. Multi-scale sliding window, proposal rejecting, scoring, and non-maximum suppression are combined to generate a modest and effective set of proposals. Experimental results demonstrate that our proposed approach generates a modest set of proposals and outperforms some state-of-the-art methods on nighttime images in terms of various evaluation metrics. Furthermore, our proposed object proposal approach can improve the detection performance and the speed of several state-of-the-art vehicle detection approaches.

Many potential applications of porous silicon nanowires (SiNWs) fabricated with metal-assisted chemical etching are highly dependent on the precise control of morphology for device optimization. However, the effects of key etching parameters, such as the amount of deposited metal catalyst, HF–oxidant molar ratio (χ), and solvent concentration, on the morphology and etching kinetics of the SiNWs still have not been fully explored. Here, the changes in the nanostructure and etch rate of degenerately doped p-type silicon in a HF–H2O2–H2O etching system with electrolessly deposited silver catalyst are systematically investigated. The surface morphology is found to evolve from a microporous and cratered structure to a uniform array of SiNWs at sufficiently high χ values. The etch rates at the nanostructure base and tip are correlated with the primary etching induced by Ag and the secondary etching induced by metal ions and diffused holes, respectively. The H2O concentration also affects the χ window where SiNWs form and the etch rates, mainly by modulating the reactant dilution and diffusion rate. By controlling the secondary etching and reactant diffusion via χ and H2O concentration, respectively, the fabrication of highly doped SiNWs with independent control of porosity from length is successfully demonstrated, which can be potentially utilized to improve the performance of SiNW-based devices.

Significant progress has been made recently in treating neurological blindness using implantable visual prostheses. However, implantable medical devices are highly invasive and subject to many safety, efficacy, and cost issues. The discovery that ultrasound (US) may be useful as a noninvasive neuromodulation tool has aroused great interest in the field of acoustic retinal prostheses (ARPs). We have investigated the responsiveness of rat retinal ganglion cells (RGCs) to low-frequency focused US stimulation (LFUS) at 2.25 MHz and characterized the neurophysiological properties of US responses by performing in vitro multielectrode array recordings. The results show that LFUS can reliably activate RGCs. The US-induced responses did not correspond to the standard light responses and varied greatly among cell types. Moreover, dual-peak responses to US stimulation were observed that have not been reported previously. The temporal response properties of RGCs, including their latency, firing rate, and response type, were modulated by the acoustic intensity. These findings suggest the presence of a temporal neuromodulation effect of LFUS and potentially open a new avenue in the development of ARP.

Microelectrode arrays play an important role in prosthetic implants for neural signal recording or applying electrical pulses stimulation to target nerve system. Safety and long-term reliability are essential requirements for microelectrode arrays applied in electrical stimulation. In design and fabrication of the microelectrode array, soft materials are generally chosen to be the substrate for the aim of achieving better compliance with the surrounding tissue while maintaining minimal damage. By flexing of the array to the surface, the array is capable of keeping a more stable electrical contact resulting in a significantly improved signal detected. In this study, we design and fabricate a flexible microelectrode array with gold as the electrode material and parylene-C as the substrate. The fabrication process of the array is presented. The in vitro electrochemical characteristics of the microelectrode are investigated by electrochemical impedance spectroscopy and cyclic voltammetry in a three-electrode electrochemical cell containing phosphate-buffered saline. Charge injection capacity measurements are carried out by multichannel systems and the CSC of the microarray is calculated. Electrochemical results showed that impedance decreased with frequency. The average impedance of the Au electrodes at 1 kHz was 36.54 ± 0.88 kΩ. The average phase angle at 1 kHz was − 73.52 ± 1.3°, and the CIC of the microelectrode was 22.3 µC/cm2. The results demonstrated that the microelectrode array performed as expected for neuronal signal recording or stimulation. With parylene-C as the substrate, the microarray has good flexibility. The electrochemical characteristics’ results show that the array has the ability to resist any corrosion on metal–electrolyte interface and has good biocompatibility. This low-cost, flexible parylene-based, gold microelectrode array shows potential for use in implant neurological signal acquisition or neurostimulation applications.