Road traffic sign detection and recognition play an important role in advanced driver assistance systems (ADAS) by providing real-time road sign perception information. In this paper, we propose an improved (Single Shot Detector) SSD algorithm via multi-feature fusion and enhancement, named MF-SSD, for traffic sign recognition. First, low-level features are fused into high-level features to improve the detection performance of small targets in the SSD. We then enhance the features in different channels to detect the target by enhancing effective channel features and suppressing invalid channel features. Our algorithm gets good results in domestic real-time traffic signs. The proposed MF-SSD algorithm is evaluated with the German Traffic Sign Recognition Benchmark (GTSRB) dataset. The experimental results show that the MF-SSD algorithm has advantages in detecting small traffic signs. Compared with existing methods, it achieves higher detection accuracy, better efficiency, and better robustness in complex traffic environment.

Webshell is a backdoor web page-based program. Malicious attackers obtain some privileges through the Webshell so as to realize the operation and control of the website. However, due to confusion coding technology, Webshell detection becomes difficult. This paper presents a Webshell detection model based on a word attention mechanism. In the model, we mainly focus on intra-line word association. After using Word2vec to vectorize the words, we use GRU (Gated Recursive Unit) and attention mechanism to train and detect the samples. The experimental results show that the model has a high detection rate and low loss function.

In this correspondence, we address the issue of direction-of-arrival (DOA) estimation for coprime multiple-input multiple-output (MIMO) radar employing mixed-resolution quantization. First, we derive the received signal model of coprime MIMO radar under mixed-resolution quantization, and utilize mixed-resolution measurements to construct an augmented signal vector via virtual array interpolation. Subsequently, we reconstruct a low-rank augmented covariance matrix without the effect of quantization error by solving an atomic norm minimization problem. Finally, we extract the DOAs of targets by applying MUSIC method on the reconstructed low-rank matrix. Unlike the existing techniques, our method not only recovers the missing correlation information, but also reduces the influence of noise and quantization error. Simulation results illustrate the advantage of the proposed approach over the existing techniques when handling mixed-resolution measurements.

In this letter, an effective method for estimating direction-of-arrival (DOA) using the nested array via mixed-resolution (MR) quantization is developed. First, we derive the output signal model of the nested array under MR quantization, and utilize MR quantized data to construct a quantized covariance matrix. Subsequently, we recover an unquantized augmented covariance matrix by formulating a rank-minimization problem in the coarray domain. Finally, we perform DOA estimation using the recovered covariance matrix. The proposed method can achieve excellent performance close to that of the existing methods using high-resolution data. Simulation results demonstrate the validity of our approach.