Visual traffic surveillance systems play important roles in intelligent transport systems nowadays. The first step of a visual traffic surveillance system usually needs to correctly detect objects from images or videos and classify them into different categories (e.g., car, truck, and bus). This paper aims to introduce a new vehicle type classification scheme on the images acquired from multi-view visual traffic surveillance sensors. Most image classification algorithms focus on maximizing the percentage of the correct predictions, which have a deficiency that the images from minority categories are prone to be misclassified as the dominant categories. To address this challenge of classifying imbalanced data acquired from visual traffic surveillance sensors, we propose a method, which integrates deep neural networks with balanced sampling in this paper. The proposed method consists of two main stages. In the first stage, data augmentation with balanced sampling is applied to alleviate the unbalanced data set problem. In the second stage, an ensemble of convolutional neural network models with different architectures is constructed with parameters learned on the augmented training data set. Experiments on the MIOvision traffic camera dataset classification challenge data set demonstrate that the proposed method is able to enhance the mean precision of all categories, in the condition of high overall accuracy, compared with the baseline algorithms.

Bi-temporal remote sensing semantic change detection (SCD) involves discerning and categorizing changes in the same geographical area across two remote sensing (RS) images taken at different times. High-performance SCD approaches typically address this task using multitask networks that simultaneously handle binary change detection (BCD) and semantic segmentation (SS). Despite significant advancements in SCD research, constructing a multitask network that fully explores the correlation between BCD and SS remains challenging. To address this, we propose a novel approach called the Multitask CNN-Transformer Network (MCTNet), tailored for SCD using bi-temporal RS images. Our Siamese network simultaneously tackles SS and BCD via three subnetworks: two for SS and one for BCD. The methodology begins with a multiscale Convolutional Neural Network (CNN) extracting local features from input images, and converting them into tokens. A Transformer module with an encoder-decoder architecture then captures long-range dependencies among these visual tokens. The extracted features are subsequently passed to multitask heads, generating predicted outputs. To ensure that the BCD results remain consistent regardless of the order of images in the input pair, we introduce spatiotemporal feature learning, enabling the acquisition of temporal-symmetric representations for BCD. Extensive experimental validation on the WHU-CD, SECOND, and HRSCD datasets demonstrates the effectiveness and efficiency of MCTNet for both SS and BCD tasks. The source code for this paper will be published on GitHub in the future ¹ .

Object detection in unmanned aerial vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate nature of UAV images and the potential synergy between them. In response, this paper proposes AD-Det, a novel framework employing a coherent coarse-to-fine strategy that seamlessly integrates two pivotal components: adaptive small object enhancement (ASOE) and dynamic class-balanced copy–paste (DCC). ASOE utilizes a high-resolution feature map to identify and cluster regions containing small objects. These regions are subsequently enlarged and processed by a fine-grained detector. On the other hand, DCC conducts object-level resampling by dynamically pasting tail classes around the cluster centers obtained by ASOE, maintaining a dynamic memory bank for each tail class. This approach enables AD-Det to not only extract regions with small objects for precise detection but also dynamically perform reasonable resampling for tail-class objects. Consequently, AD-Det enhances the overall detection performance by addressing the challenges of scale variations and class imbalance in UAV images through a synergistic and adaptive framework. We extensively evaluate our approach on two public datasets, i.e., VisDrone and UAVDT, and demonstrate that AD-Det significantly outperforms existing competitive alternatives. Notably, AD-Det achieves a $37.5\%$ average precision (AP) on the VisDrone dataset, surpassing its counterparts by at least $3.1\%$.