Search

Fish species recognition is crucial to identifying the abundance of fish species in a specific area, controlling production management, and monitoring the ecosystem, especially identifying the endangered species, which makes accurate fish species recognition essential. In this work, the fish species recognition problem is formulated as an object detection model to handle multiple fish in a single image, which is challenging to classify using a simple classification network. The proposed model consists of MobileNetv3-large and VGG16 backbone networks and an SSD detection head. Moreover, a class-aware loss function is proposed to solve the class imbalance problem of our dataset. The class-aware loss takes the number of instances in each species into account and gives more weight to those species with a smaller number of instances. This loss function can be applied to any classification or object detection task with an imbalanced dataset. The experimental result on the large-scale reef fish dataset, SEAMAPD21, shows that the class-aware loss improves the model over the original loss by up to 79.7%. The experimental result on the Pascal VOC dataset also shows the model outperforms the original SSD object detection model.

The pursuit of autonomous driving relies on developing perception systems capable of making accurate, robust, and rapid decisions to interpret the driving environment effectively. Object detection is crucial for understanding the environment at these systems' core. While 2D object detection and classification have advanced significantly with the advent of deep learning (DL) in computer vision (CV) applications, they fall short in providing essential depth information, a key element in comprehending driving environments. Consequently, 3D object detection becomes a cornerstone for autonomous driving and robotics, offering precise estimations of object locations and enhancing environmental comprehension. The CV community's growing interest in 3D object detection is fueled by the evolution of DL models, including Convolutional Neural Networks (CNNs) and Transformer networks. Despite these advancements, challenges such as varying object scales, limited 3D sensor data, and occlusions persist in 3D object detection. To address these challenges, researchers are exploring multimodal techniques that combine information from multiple sensors, such as cameras, radar, and LiDAR, to enhance the performance of perception systems. This survey provides an exhaustive review of multimodal fusion-based 3D object detection methods, focusing on CNN and Transformer-based models. It underscores the necessity of equipping fully autonomous vehicles with diverse sensors to ensure robust and reliable operation. The survey explores the advantages and drawbacks of cameras, LiDAR, and radar sensors. Additionally, it summarizes autonomy datasets and examines the latest advancements in multimodal fusion-based methods. The survey concludes by highlighting the ongoing challenges, open issues, and potential directions for future research. [ABSTRACT FROM AUTHOR]

The development of wearable technology, which enables motion tracking analysis for human movement outside the laboratory, can improve awareness of personal health and performance. This study used a wearable smart sock prototype to track foot–ankle kinematics during gait movement. Multivariable linear regression and two deep learning models, including long short-term memory (LSTM) and convolutional neural networks, were trained to estimate the joint angles in sagittal and frontal planes measured by an optical motion capture system. Participantspecific models were established for ten healthy subjects walking on a treadmill. The prototype was tested at various walking speeds to assess its ability to track movements for multiple speeds and generalize models for estimating joint angles in sagittal and frontal planes. LSTM outperformed other models with lower mean absolute error (MAE), lower root mean squared error, and higher R-squared values. The average MAE score was less than 1.138° and 0.939° in sagittal and frontal planes, respectively, when training models for each speed and 2.15° and 1.14° when trained and evaluated for all speeds. These results indicate wearable smart socks to generalize foot–ankle kinematics over various walking speeds with relatively low error and could consequently be used to measure gait parameters without the need for a lab-constricted motion capture system. [ABSTRACT FROM AUTHOR]

LiDAR is a commonly used sensor for autonomous driving to make accurate, robust, and fast decision-making when driving. The sensor is used in the perception system, especially object detection, to understand the driving environment. Although 2D object detection has succeeded during the deep-learning era, the lack of depth information limits understanding of the driving environment and object location. Three-dimensional sensors, such as LiDAR, give 3D information about the surrounding environment, which is essential for a 3D perception system. Despite the attention of the computer vision community to 3D object detection due to multiple applications in robotics and autonomous driving, there are challenges, such as scale change, sparsity, uneven distribution of LiDAR data, and occlusions. Different representations of LiDAR data and methods to minimize the effect of the sparsity of LiDAR data have been proposed. This survey presents the LiDAR-based 3D object detection and feature-extraction techniques for LiDAR data. The 3D coordinate systems differ in camera and LiDAR-based datasets and methods. Therefore, the commonly used 3D coordinate systems are summarized. Then, state-of-the-art LiDAR-based 3D object-detection methods are reviewed with a selected comparison among methods. [ABSTRACT FROM AUTHOR]

Three-dimensional object detection is crucial for autonomous driving to understand the driving environment. Since the pooling operation causes information loss in the standard CNN, we designed a wavelet-multiresolution-analysis-based 3D object detection network without a pooling operation. Additionally, instead of using a single filter like the standard convolution, we used the lower-frequency and higher-frequency coefficients as a filter. These filters capture more relevant parts than a single filter, enlarging the receptive field. The model comprises a discrete wavelet transform (DWT) and an inverse wavelet transform (IWT) with skip connections to encourage feature reuse for contrasting and expanding layers. The IWT enriches the feature representation by fully recovering the lost details during the downsampling operation. Element-wise summation was used for the skip connections to decrease the computational burden. We trained the model for the Haar and Daubechies (Db4) wavelets. The two-level wavelet decomposition result shows that we can build a lightweight model without losing significant performance. The experimental results on KITTI's BEV and 3D evaluation benchmark show that our model outperforms the PointPillars-based model by up to 14% while reducing the number of trainable parameters. [ABSTRACT FROM AUTHOR]

A deep‐learning‐based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle‐of‐arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estimators utilised in these areas require accurate estimates of the number of sources for enhanced performance. Herein, a robust method that performs well under the existence of coherent sources is developed. The proposed method is based on deep learning and it is shown to perform better than state‐of‐the‐art versions of the Akaike Information Criteria (AIC), Minimum Description Length (MDL), and Exponentially Embedded Families (EEF) estimators, which employ spatial smoothing of the covariance matrix to handle coherent signals. [ABSTRACT FROM AUTHOR]

A significant challenge in object detection is accurate identification of an object’s position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications. [ABSTRACT FROM AUTHOR]

This paper presents a retrospective of the benchmark testing methodologies developed and accumulated into the stretch sensor tool kit (SSTK) by the research team during the Closing the Wearable Gap series of studies. The techniques developed to validate stretchable soft robotic sensors (SRS) as a means for collecting human kinetic and kinematic data at the foot-ankle complex and at the wrist are reviewed. Lessons learned from past experiments are addressed, as well as what comprises the current SSTK based on what the researchers learned over the course of multiple studies. Three core components of the SSTK are featured: (a) material testing tools, (b) data analysis software, and (c) data collection devices. Results collected indicate that the stretch sensors are a viable means for predicting kinematic data based on the most recent gait analysis study conducted by the researchers (average root mean squared error or RMSE = 3.63°). With the aid of SSTK defined in this study summary and shared with the academic community on GitHub, researchers will be able to undergo more rigorous validation methodologies of SRS validation. A summary of the current state of the SSTK is detailed and includes insight into upcoming experiments that will utilize more sophisticated techniques for fatigue testing and gait analysis, utilizing SRS as the data collection solution. [ABSTRACT FROM AUTHOR]

Since the state-of-the-art deep learning algorithms demand a large training dataset, which is often unavailable in some domains, the transfer of knowledge from one domain to another has been a trending technique in the computer vision field. However, this method may not be a straight-forward task considering several issues such as original network size or large differences between the source and target domain. In this paper, we perform transfer learning for semantic segmentation of off-road driving environments using a pre-trained segmentation network called DeconvNet. We explore and verify two important aspects regarding transfer learning. First, since the original network size was very large and did not perform well for our application, we proposed a smaller network, which we call the light-weight network. This light-weight network is half the size to the original DeconvNet architecture. We transferred the knowledge from the pre-trained DeconvNet to our light-weight network and fine-tuned it. Second, we used synthetic datasets as the intermediate domain before training with the real-world off-road driving data. Fine-tuning the model trained with the synthetic dataset that simulates the off-road driving environment provides more accurate results for the segmentation of real-world off-road driving environments than transfer learning without using a synthetic dataset does, as long as the synthetic dataset is generated considering real-world variations. We also explore the issue whereby the use of a too simple and/or too random synthetic dataset results in negative transfer. We consider the Freiburg Forest dataset as a real-world off-road driving dataset. [ABSTRACT FROM AUTHOR]