This current review article focuses on recent contributions to on-site forensic investigations. Portable and potentially portable methods are presented and critically discussed about (bio)chemical ...trace analysis and studies performed outside the controlled laboratory environment to rapidly help in crime scene inquiries or forensic intelligence purposes. A wide range of approaches including electrochemical sensors, microchip electrophoresis, ambient ionization on portable mass spectrometers, handheld Raman and NIR instruments as well as and point-of-need devices, like paper-based platforms, for in-field analysis of latent evidences, controlled substances, drug screening, hazards, and others to assist in law enforcements and solving crime more efficiently are highlighted. The covered examples have successfully demonstrated the huge potential of portable devices for on-site applications. Future investigations should consider analytical validation to compete equality and even replace current gold standard methods.
Display omitted
•Electrochemical sensors offer good sensitivity for abuse drugs and explosives.•Paper-based devices have revealed desirable performance for point-of-care testing.•NIR and RAMAN instruments have allowed fast screening at the point-of-need.•Portable MS instruments have exhibited good performance for on-site forensic applications.•Electrophoresis chips have provided excellent ability for STR genotyping.
Self-driving cars: A survey Badue, Claudine; Guidolini, Rânik; Carneiro, Raphael Vivacqua ...
Expert systems with applications,
03/2021, Volume:
165
Journal Article
Peer reviewed
We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be ...categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the decision-making system. The perception system is generally divided into many subsystems responsible for tasks such as self-driving-car localization, static obstacles mapping, moving obstacles detection and tracking, road mapping, traffic signalization detection and recognition, among others. The decision-making system is commonly partitioned as well into many subsystems responsible for tasks such as route planning, path planning, behavior selection, motion planning, and control. In this survey, we present the typical architecture of the autonomy system of self-driving cars. We also review research on relevant methods for perception and decision making. Furthermore, we present a detailed description of the architecture of the autonomy system of the self-driving car developed at the Universidade Federal do Espírito Santo (UFES), named Intelligent Autonomous Robotics Automobile (IARA). Finally, we list prominent self-driving car research platforms developed by academia and technology companies, and reported in the media.
•Recently developments of autonomous driving from academic and industry point of view.•Breakdown of the main aspects comprising autonomous driving and their evolution.•Autonomous driving architecture review and proposal.
The adulteration of whiskey with analgesics and sedation drugs has been a common practice to prevent hangover the following day and promote loss of consciousness. In both situations, the portable and ...low cost detection platforms are of paramount importance for forensic investigations. This report describes the use of electrochemical paper‐based analytical devices (ePADs) fabricated by pencil drawing for detecting metamizole, paracetamol and midazolam maleate in whiskey. Different types of paper substrates and graphite pencils were initially characterized with ferrocyanide. The best results were achieved using vegetal paper and Aquarelle/6B pencils. ePADs revealed a decrease in current signal indicating a short lifetime, thus limiting their use to disposable sensors. Despite the short lifetime, the graphite pencil ePADs revealed good electrochemical reproducibility (RSD=3.3 %). The forensic feasibility of the proposed ePADs was demonstrated through the analysis of metamizole and paracetamol in whiskey. The limit of detection (LOD) achieved for paracetamol and metamizole were 45 and 20 mg L−1, respectively. ePADs were also tested to detect midazolam maleate in whiskey. The signal recorded exhibited linear correlation in a wide concentration range (25–1000 mg L−1) and a LOD of ca. 5 mg L−1. Considering the disposability and operational simplicity, ePADs offer a good strategy for detecting adulterations in alcoholic beverages at the point‐of‐need.
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the ...alignment of the intermediate features proven to be promising, achieving state-of-the-art results. However, these methods are laborious to implement and hard to interpret. Although promising, there is still room for improvements to close the performance gap toward the upper-bound (when training with the target data). In this work, we propose a method to generate an artificial dataset in the target domain to train an object detector. We employed two unsupervised image translators (CycleGAN and an AdaIN-based model) using only annotated data from the source domain and non-annotated data from the target domain. Our key contributions are the proposal of a less complex yet more effective method that also has an improved interpretability. Results on real-world scenarios for autonomous driving show significant improvements, outperforming state-of-the-art methods in most cases, further closing the gap toward the upper-bound.
•A simple yet effective method for detecting objects on unsupervised domain adaptation.•Artificially generated images are useful for unsupervised domain adaptation.•An extensive comparison with the state-of-the-art is provided.•Experiments in three scenarios: synthetic data, adverse weather, and cross-camera.
Deep learning has become a standard approach to machine vision in recent years. Despite several advances, it requires large amounts of annotated data. Nonetheless, in many applications, large-scale ...data acquisition and annotation is expensive and data imbalance is an intrinsic problem. To address these challenges, we propose a novel synthetic database generation method that only requires (i) arbitrary natural images, i.e., does not demand real images from the target domain, and (ii) templates of the traffic signs. Our method does not aim at overcoming the training with real data but to be a compatible option when there is a lack of real data. Results with data of multiple countries show that the synthetic database generated without human effort is effective for training a deep traffic sign detector. On large datasets, training with a fully synthetic dataset almost matches the performance of training with a real one. When compared to training with a smaller dataset of real images, training with synthetic images increased the accuracy by 12.25%. The proposed method also improves the performance of the detector when target-domain data are available.
Understanding the basic properties of pristine carbon nitride electrodes is of great importance for their further applications as supercapacitor materials. To this end, a comparative study of ...unmodified carbon nitride is crucial to understand the difference between the bare material and its composite counterparts described in the literature. Therefore, the aim of this paper is to explore the electrochemical behaviour of casting-produced C
N
electrodes using cyclic voltammetry, charge/discharge curves and impedance spectroscopy. The results from this study show a capacitance value of 113.7 F g
at 0.2 A g
with an impressive retention of 89.2% after 5000 charge and discharge cycles at 3.0 A g
. In addition, this material shows a large amount of specific energy (76.5 W h kg
) at an operation power of 11.9 W kg
, decreasing only 10.7% due to the electrochemical aging process. Hence, C
N
constitutes a long-life pristine material with a large amount of energy and a moderate operation power with better performance than other C
N
-based composites found in the literature. These results are important to gain a better understanding of the inherent properties of carbon nitride - to further design composites with higher specific capacitance, longer lifetime, and specific energy.
•Paper shreds matching via self-supervised deep learning.•Training with simulated cuts is effective for real-shredded documents.•A new public dataset with 100 strip-shredded documents (2292 ...shreds).•Accurate (over 90% accuracy) reconstruction of 100 mixed shredded documents.
The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solutions compromise significantly time performance. The solution presented in this work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario: the reconstruction of several mixed shredded documents at once. In our approach, the compatibility evaluation is modeled as a two-class (valid or invalid) pattern recognition problem. The model is trained in a self-supervised manner on samples extracted from simulated-shredded documents, which obviates manual annotation. Experimental results on three datasets – including a new collection of 100 strip-shredded documents produced for this work – have shown that the proposed method outperforms the competing ones on complex scenarios, achieving accuracy superior to 90%.
•Handling Pedestrians in Self-Driving Cars using Image Tracking and Frenét Frames.•The method is safer and more efficient than systems without tracking functionality.•Tracking pedestrians enables ...early decision capability.•Our self-driving car was evaluated in both simulated and real-world scenarios.
Display omitted
The development of intelligent autonomous cars is of great interest. A particular and challenging problem is to handle pedestrians, for example, crossing or walking along the road. Since pedestrians are one of the most fragile elements in traffic, a reliable pedestrian detection and handling system is mandatory. The current pedestrian handling system of our autonomous cars suffers from the limitation of the pure detection-based systems, i.e., it limits the autonomous car system to make decisions based only on the very present moment. This work improves the pedestrian handling systems by incorporating an object tracker with the aim of predicting the pedestrian’s behavior. With this knowledge, the autonomous car can better decide the time to stop and to start moving, providing a more comfortable, efficient, and safer driving experience. The proposed method was augmented with a path generator, based on Frenét Frames, and incorporated to our self-driving car in order to enable a better decision making and to enable overtaking pedestrians. The behaviour of our self-driving car was evaluated in both simulated and real-world scenarios. Results showed the proposed system is safer and more efficient than the system without tracking functionality due to the early decision capability.