This work-in-progress research paper focuses on the first-year engineering teams' peer evaluation processes. Teamwork has been identified as a necessary skill for professional engineers and thus an ABET learning outcome. Reliable systematic processes to assess teamwork effectiveness are crucial for improving team outcomes and identifying dysfunctional teams in a classroom setting. Evaluating team effectiveness and identifying dysfunctional teams has been traditionally done through peer evaluations. However, there is a lack of evidence on what/how students' perceptions of effective teammates and functional teams impact peer evaluations. Identifying common indicators and behaviors that students consider when evaluating their peers is a first step to exploring the reliability of peers as evaluators, understanding potential biases, and using peer feedback to investigate dysfunctional teams. This paper aims to take this first step and will explore the following question: “What evidence do students provide to describe poor team behaviors?” The study was conducted at a large, public, urban, Midwestern R1 institution. For the first two semesters of the engineering curriculum, students are required to participate actively in team-based projects as part of engineering design thinking courses. The following procedure was used to answer our research question. Students were first asked to respond to a peer evaluation instrument based on a four-factor (Interdependency, Goal setting, Potency, and Trust) team effectiveness model. Then, students were asked to grade their teammates on a cumulative score of 100 for the team and support their distribution choices with open-ended comments on team behaviors. We started with an analysis of students' comments regarding negative behaviors to support their low rating for each teammate. We selected comments that had a high misalignment between the model-based peer evaluation and corresponding distributed ratings, resulting in a sample of 93 students. Next, we conducted inductive coding on the comments to identify frequently mentioned negative behaviors and see if these behaviors were addressed in the model-based peer evaluation. Eight major themes emerged from students' comments.

The efficient collection and transmission of large-scale seismic data are crucial aspects of seismic monitoring and large seismic surveys in exploration seismology, which is becoming increasingly important due to the proliferation of sensor networks and seismic monitoring equipment. Compressed sensing (CS) theory enhances the efficiency of seismic data acquisition and transmission by reducing the volume of data required, thereby circumventing the limitations imposed by the Nyquist sampling theorem. However, traditional CS methods have limitations in accurately reconstructing data and overlook the correlation between the measurement matrix and the signal itself. Herein, a seismic data acquisition method based on CS and deep learning has been proposed in this study, namely, the convolutional neural network-based compressed sensing method (CSCNN). The CSCNN framework comprises sampling and reconstruction blocks. The sampling block employs a convolutional layer to perform an observational function in CS systems. The reconstruction block comprises a deconvolution layer used for the preliminary reconstruction of seismic data and employs alternating cascaded residual blocks (RBs) and introduced attention mechanism (AM) to enhance the accuracy of seismic data reconstruction. Results demonstrate that, the CSCNN method outperforms traditional reconstruction methods in effectively reconstructing data at equivalent compression ratios, yielding a higher signal-to-noise ratio (SNR) and reduced error.

Abstract The development of future wireless communications systems faces a big challenge of spectrum scarcity. Co‐existence of radar and communications systems is thus of great interest. In this work, the performance of a communications system with hardware impairment (HWI) as well as interference from radar systems will be studied. The impact of radar interference, I/Q imbalance coefficients as well as channel state information (CSI) will be evaluated in terms of outage probability and symbol error rate. Simulation results prove that the proposed detectors provide explicit and conducive insights for further exploration of joint radar‐communications designs.

We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image snippets, leading to severe error accumulation. Global information is crucial for alleviating accumulated errors. However, it is challenging to effectively preserve such information for end-to-end systems. To deal with this challenge, we design an adaptive memory module, which progressively and adaptively saves the information from local to global in a neural analogue of memory, enabling our system to process long-term dependency. Benefiting from global information in the memory, previous results are further refined by an additional refining module. With the guidance of previous outputs, we adopt a spatial-temporal attention to select features for each view based on the co-visibility in feature domain. Specifically, our architecture consisting of Tracking, Remembering and Refining modules works beyond tracking. Experiments on the KITTI and TUM-RGBD datasets demonstrate that our approach outperforms state-of-the-art methods by large margins and produces competitive results against classic approaches in regular scenes. Moreover, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic algorithms tend to fail.

In this article, we propose a visual simultaneous localization and mapping (SLAM) method by predicting and updating line flows that represent sequential 2-D projections of 3-D line segments. While feature-based SLAM methods have achieved excellent results, they still face problems in challenging scenes containing occlusions, blurred images, and repetitive textures. To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3-D line along the temporal dimension, which has been neglected in prior SLAM systems. Thanks to this line flow representation, line segments in a new frame can be predicted according to their corresponding 3-D lines and their predecessors along the temporal dimension. We create, update, merge, and discard line flows on-the-fly. We model the proposed line flow based SLAM (LF-SLAM) using a Bayesian network. Extensive experimental results demonstrate that the proposed LF-SLAM method achieves state-of-the-art results due to the utilization of line flows. Specifically, LF-SLAM obtains good localization and mapping results in challenging scenes with occlusions, blurred images, and repetitive textures.

We propose to construct a view graph to excavate the information of the whole given sequence for absolute camera pose estimation. Specifically, we harness GNNs to model the graph, allowing even non-consecutive frames to exchange information with each other. Rather than adopting the regular GNNs directly, we redefine the nodes, edges, and embedded functions to fit the relocalization task. Redesigned GNNs cooperate with CNNs in guiding knowledge propagation and feature extraction respectively to process multi-view high-dimension image features iteratively at different levels. Besides, a general graph-based loss function beyond constraints between consecutive views is employed for training the network in an end-to-end fashion. Extensive experiments conducted on both indoor and outdoor datasets demonstrate that our method outperforms previous approaches especially in large-scale and challenging scenarios.

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.

We propose to leverage the local information in a image sequence to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential images to alleviate uncertainty due to visual ambiguities by incorporating a visual odometry (VO) component. Specifically, we introduce two effective steps called content-augmented pose estimation and motion-based refinement. The content-augmentation step focuses on alleviating the uncertainty of pose estimation by augmenting the observation based on the co-visibility in local maps built by the VO stream. Besides, the motion-based refinement is formulated as a pose graph, where the camera poses are further optimized by adopting relative poses provided by the VO component as additional motion constraints. Thus, the global consistency can be guaranteed. Experiments on the public indoor 7-Scenes and outdoor Oxford RobotCar benchmark datasets demonstrate that benefited from local information inherent in the sequence, our approach outperforms state-of-the-art methods, especially in some challenging cases, e.g., insufficient texture, highly repetitive textures, similar appearances, and over-exposure.

We present a robust tracking method based on many-to-many image superpixel matching (MMM). Our MMM tracker represents a target and its background using two sets of superpixels. Multiple hypotheses for superpixel matching are considered for better tracking performance. For each superpixel in an input image, k matching candidates are searched in the representative sets using approximate k -NN searching. The degree of matching is measured using foreground likelihood and matching probability assignment. The superpixel matching results are projected onto a displacement confidence map that depicts the motion probabilities of all the superpixels. During the projection, the displacements confidence of the superpixels are regularized by kernel methods. We estimate the target position by searching for the maximum probability on the displacement confidence map. The experimental results confirm that our superpixel matching achieves better performance than other trackers.

We present a new pedestrian detection algorithm that considers multiple information sources. Appearance-based detection methods face difficulties such as appearance variations and occlusions. Shape-based methods can have false positives on shadows since they usually have similar shapes with foreground objects. To deal with these problems, we use appearance, motion, and shadow information simultaneously in our detection method. We detect pedestrians using shape information of both foreground and shadow regions. Then, we filter the detection results based on motion information if available. The proposed method gives low false positives due to the integration of multiple information sources. Moreover, it alleviates the problem brought by occlusion since casted shadows are observable when foreground objects are occluded. Our experimental results show that the proposed algorithm provides good performance in difficult situations.

Female enrollment in engineering in the United States has remained at or below 20% for decades. Enrollment of students from traditionally underrepresented groups has also remained below desired level for years. A systematic understanding of important factors leading to persistence and success in undergraduate engineering programs for female and underrepresented minority students would be very valuable for recruiting, retaining and educating young engineers with diverse perspectives. This paper discusses the significant predictors for retention and academic performance of female engineering students, and reports the difference in comparison with male engineering students. Similar results on the important predictors for retention and performance of underrepresented minority engineering students will also be reported and compared with the ethnic majority students. The findings from this study suggest it is potentially advantageous to develop student success models specific for female or minority engineering student populations, rather than using the same model developed for the whole population. New knowledge obtained through this study will lead to the development of necessary strategies, interventions or programs to help improve retention and academic success of our engineering students.

Developing students teaming skills has become common place in engineering education as a pedagogical tool to facilitate learning of technical content as well as to prepare students for professional practice. Engineering faculty typically determine the degree to which students have had an effective team experience by indirect methods such as homework or project grades along with self report team member peer-evaluations. Such methods tend to place a greater emphasis on the outcome (or product) of teaming rather than on the process of teaming itself. The use of standalone peer-evaluations to indirectly determine team effectiveness has also been shown to be problematic, since students are not typically taught how to properly evaluate their peers. This lack of training generally results in a significant amount evaluation bias. This research presents a theoretical framework to indirectly measure team effectiveness using a calibrated peer evaluation system The system provides students feedback on their rating ability as well as quantifies (as a 1st order approximation) their evaluation bias. The system can be used by faculty for early identification of dysfunctional teams as well as to determine the degree to which students are engaged in effective team behaviors.

Object tracking and segmentation find a wide range of applications in robotics. Tracking and segmentation are difficult in cluttered and dynamic backgrounds. We propose a tracking and segmentation algorithm in which tracking and segmentation are performed consecutively. We separate input images into disjoint patches using an efficient oversegmentation algorithm. Objects and their background are described by bags of patches. We classify the patches in a new frame by searching k nearest neighbors. K-d trees are constructed using these patches to reduce computational complexity. Target location is estimated coarsely by running the mean-shift algorithm. Based on the estimated locations, we classify the patches again using appearance and spatial information. This strategy out-performs direct segmentation of patches based on appearance information only. Experimental results show that the proposed algorithm provides good performance on difficult sequences with clutter.

We present a new approach for robust and efficient tracking by incorporating the efficiency of the mean-shift algorithm with the multihypothesis characteristics of particle filtering in an adaptive manner. The aim of the proposed algorithm is to cope with problems that were brought about by sudden motions and distractions. The mean-shift tracking algorithm is robust and effective when the representation of a target is sufficiently discriminative, the target does not jump beyond the bandwidth, and no serious distractions exist. We propose a novel two-stage motion estimation method that is efficient and reliable. If a sudden motion is detected by the motion estimator, some particle-filtering-based trackers can be used to outperform the mean-shift algorithm, at the expense of using a large particle set. In our approach, the mean-shift algorithm is used, as long as it provides reasonable performance. Auxiliary particles are introduced to cope with distractions and sudden motions when such threats are detected. Moreover, discriminative features are selected according to the separation of the foreground and background distributions when threats do not exist. This strategy is important, because it is dangerous to update the target model when the tracking is in an unsteady state. We demonstrate the performance of our approach by comparing it with other trackers in tracking several challenging image sequences.

We present a patch-based tracking algorithm in which both appearance and spatial information are taken into account for target localization. We decompose a target into several patches based on appearance similarity and spatial distribution. Each patch has its distinctive appearance and spatial distribution. Appearance information is described by kernels which are non-parametric; while spatial information is represented by spatial Gaussians. The overall motion is estimated by mean shift algorithm. The motion is refined based on the likelihood images computed using pixel classification. The proposed tracker provides better position and likelihood images.

The covariance tracker finds the targets in consecutive frames by global searching. Covariance tracking has achieved impressive successes thanks to its ability of capturing spatial and statistical properties as well as the correlations between them. Nevertheless, the covariance tracker is relatively inefficient due to its heavy computational cost of model updating and comparing the model with the covariance matrices of the candidate regions. Moreover, it is not good at dealing with articulated object tracking since integral histograms are employed to accelerate the searching process. In this work, we aim to alleviate the computational burden by selecting appropriate tracking approaches. We compute foreground probabilities of pixels and localize the target by local searching when the tracking is in steady states. Covariance tracking is performed when distractions, sudden motions or occlusions are detected. Different from the traditional covariance tracker, we use log-Euclidean metrics instead of Riemannian invariant metrics which are more computationally expensive. The proposed tracking algorithm has been verified on many video sequences. It proves more efficient than the covariance tracker. It is also effective in dealing with occlusions, which are an obstacle for local mode-seeking trackers such as the mean-shift tracker.

Gait recognition has recently gained attention as an effective approach to identify individuals at a distance from a camera. Most existing gait recognition algorithms assume that people have been tracked and silhouettes have been segmented successfully. Tacking and segmentation are, however, very difficult especially for articulated objects such as human beings. Therefore, we present an integrated algorithm for tracking and segmentation supported by gait recognition. After the tracking module produces initial results consisting of bounding boxes and foreground likelihood images, the gait recognition module searches for the optimal silhouette-based gait models corresponding to the results. Then, the segmentation module tries to segment people out using the provided gait silhouette sequence as shape priors. Experiments on real video sequences show the effectiveness of the proposed approach.

We extend the standard mean-shift tracking algorithm to an adaptive tracker by selecting reliable features from color and shape-texture cues according to their descriptive ability. The target model is updated according to the similarity between the initial and current models, and this makes the tracker more robust. The proposed algorithm has been compared with other trackers using challenging image sequences, and it provides better performance.

This paper presents a novel coarse-to-fine global localization approach inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by scale-invariant transformation feature descriptors are used as natural landmarks. They are indexed into two databases: a location vector space model (LVSM) and a location database. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the LVSM is fast, but not accurate enough, whereas localization from the location database using a voting algorithm is relatively slow, but more accurate. The integration of coarse and fine stages makes fast and reliable localization possible. If necessary, the localization result can be verified by epipolar geometry between the representative view in the database and the view to be localized. In addition, the localization system recovers the position of the camera by essential matrix decomposition. The localization system has been tested in indoor and outdoor environments. The results show that our approach is efficient and reliable.

This paper presents a novel approach using combined features to retrieve images containing specific objects, scenes or buildings. The content of an image is characterized by two kinds of features: Harris-Laplace interest points described by the SIFT descriptor and edges described by the edge color histogram. Edges and corners contain the maximal amount of information necessary for image retrieval. The feature detection in this work is an integrated process: edges are detected directly based on the Harris function; Harris interest points are detected at several scales and Harris-Laplace interest points are found using the Laplace function. The combination of edges and interest points brings efficient feature detection and high recognition ratio to the image retrieval system. Experimental results show this system has good performance.

This paper presents a novel coarse-to-fine global localization approach that is inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by SIFT descriptors are used as natural landmarks. These descriptors are indexed into two databases: an inverted index and a location database. The inverted index is built based on a visual vocabulary learned from the feature descriptors. In the location database, each location is directly represented by a set of scale invariant descriptors. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the inverted index is fast but not accurate enough; whereas localization from the location database using voting algorithm is relatively slow but more accurate. The combination of coarse and fine stages makes fast and reliable localization possible. In addition, if necessary, the localization result can be verified by epipolar geometry between the representative view in database and the view to be localized. Experimental results show that our approach is efficient and reliable.