<span lang="EN-US">Pedestrian detection has so far achieved great success in normal illumination, while pedestrians captured in extreme weather are often ignored. This paper investigates the importance of studying the effects of weather conditions on the recognition task, such as blurring and low contrast. Many image restoration techniques have recently been proposed, but are still insufficient to remove weather effects from images. We present our strong new pedestrian recognition system against climate situations, which is based on locating contours cues by applying multiple edge filters and extracting multiple features from images such as census transform (CT), modified census transform (MCT), and local gradient pattern (LGP) without performing any image restoration algorithm. The next stage involves finding the most discriminative characteristics using feature selection (FS) techniques. Finally, we use the final feature vector as an input to a radial basis function-based support vector machine classifier (RbfSVM) for pedestrian recognition. Experiments are performed on the daimler pedestrian classification benchmark dataset. Results show that the area under the curve (AUC) and the detection rate of our model are less affected by weather conditions compared to other common models like histogram of oriented gradients (HOG) and gabor filter bank (GFB) detectors.</span>

<p>Wireless sensor networks (WSN) are made up of an important number of sensors, called nodes, distributed in random way in a concerned monitoring area. All sensor nodes in the network are mounted with limited energy sources, which makes energy harvesting on top of the list of issues in WSN. A poor communication architecture can result in excessive consumption, reducing the network lifetime and throughput. Centralizing data collection and the introduction of gateways (GTs), to help cluster heads (CHs), improved WSN life time significantly. However, in vast regions, misplacement and poor distribution of GTs wastes a huge amount of energy and decreases network’s performances. In this work, we describe a reliable and dynamic with energy-awareness routing (RDEAR) protocol that provides a new GT’s election approach taking into consideration CHs density, transmission distance and energy. Applied on 20 different networks, RDEAR reduced the overall energy consumption, increased stability zone and network life time as well as other compared metrics. Our proposed approach increased network’s throughput up to 75.92% , 67.7% and 9.78% compared to the low energy adaptive clustering hierarchy (LEACH), distributed energy efficient clustering (DEEC) and static multihop routing (SMR), protocols, respectively.</p>

The diverse applications of the internet of things (IoT) require adaptable routing protocol able to cope with several constraints. Thus, RPL protocol was designed to meet the needs for IoT networks categorized as low power and lossy networks (LLN). RPL uses an objective function based on specific metrics for preferred parents selection through these packets are sent to root. The single routing metric issue generally doesn’t satisfy all routing performance requirements, whereas some are improved others are degraded. In that purpose, we propose a hybrid objective function with empirical stability aware (HOFESA), implemented in the network layer of the embedded operating system CONTIKI, which combines linearly three weighty metrics namely hop count, RSSI and node energy consumption. Also, To remedy to frequent preferred parents changes problems caused by taking into account more than one metric, our proposal relies on static and empirical thresholds. The designed HOFESA, evaluated under COOJA emulator against Standard-RPL and EC-OF, showed a packet delivery ratio improvement, a decrease in the power consumption, the convergence time and DIO control messages as well as it gives network stability through an adequate churn.

Pedestrian tracking and detection have become critical aspects of advanced driver assistance systems (ADASs), due to their academic and commercial potential. Their objective is to locate various pedestrians in videos and assign them unique identities. The data association task is problematic, particularly when dealing with inter-pedestrian occlusion. This occurs when multiple pedestrians cross paths or move too close together, making it difficult for the system to identify and track individual pedestrians. Inaccurate tracking can lead to false alarms, missed detections, and incorrect decisions. To overcome this challenge, our paper focuses on improving data association in our pedestrian detection system’s Deep-SORT tracking algorithm, which is solved as a linear optimization problem using a newly generated cost matrix. We introduce a set of new data association cost matrices that rely on metrics such as intersections, distances, and bounding boxes. To evaluate trackers in real time, we use YOLOv5 to identify pedestrians in images. We also perform experimental evaluations on the Multiple Object Tracking 17 (MOT17) challenge dataset. The proposed cost matrices demonstrate promising results, showing an improvement in most MOT performance metrics compared to the default intersection over union (IOU) data association cost matrix.

No abstract