Convolutional Siamese neural networks have been recently used to track objects using deep features. Siamese architecture can achieve real time speed, however it is still difficult to find a Siamese architecture that maintains the generalization capability, high accuracy and speed while decreasing the number of shared parameters especially when it is very deep. Furthermore, a conventional Siamese architecture usually processes one local neighborhood at a time, which makes the appearance model local and non-robust to appearance changes. To overcome these two problems, this paper proposes DensSiam, a novel convolutional Siamese architecture, which uses the concept of dense layers and connects each dense layer to all layers in a feed-forward fashion with a similarity-learning function. DensSiam also includes a Self-Attention mechanism to force the network to pay more attention to the non-local features during offline training. Extensive experiments are performed on four tracking benchmarks: OTB2013 and OTB2015 for validation set; and VOT2015, VOT2016 and VOT2017 for testing set. The obtained results show that DensSiam achieves superior results on these benchmarks compared to other current state-of-the-art methods.

Recently, our world witnessed major events that attracted a lot of attention towards the importance of automatic crowd scene analysis. For example, the COVID-19 breakout and public events require an automatic system to manage, count, secure, and track a crowd that shares the same area. However, analyzing crowd scenes is very challenging due to heavy occlusion, complex behaviors, and posture changes. This paper surveys deep learning-based methods for analyzing crowded scenes. The reviewed methods are categorized as (1) crowd counting and (2) crowd actions recognition. Moreover, crowd scene datasets are surveyed. In additional to the above surveys, this paper proposes an evaluation metric for crowd scene analysis methods. This metric estimates the difference between calculated crowed count and actual count in crowd scene videos.

Visual tracking is a difficult and challenging problem, for numerous reasons such as small object size, pose angle variations, occlusion, and camera motion. Object tracking has many real-world applications such as surveillance systems, moving organs in medical imaging, and robotics. Traditional tracking methods lack a recovery mechanism that can be used in situations when the tracked objects drift away from ground truth. In this paper, we propose a novel framework for tracking moving objects based on a composite framework and a reporter mechanism. The composite framework tracks moving objects using different trackers and produces pairs of forward/backward tracklets. A robustness score is then calculated for each tracker using its forward/backward tracklet pair to find the most reliable moving object trajectory. The reporter serves as the recovery mechanism to correct the moving object trajectory when the robustness score is very low, mainly using a combination of particle filter and template matching. The proposed framework can handle partial and heavy occlusions; moreover, the structure of the framework enables integration of other user-specific trackers. Extensive experiments on recent benchmarks show that the proposed framework outperforms other current state-of-the-art trackers due to its powerful trajectory analysis and recovery mechanism; the framework improved the area under the curve from 68% to 70.8% on OTB-100 benchmark.

We propose NullSpaceNet, a novel network that maps from the pixel-level image to a joint-nullspace, as opposed to the traditional feature space. The features in the proposed learned joint-nullspace have clearer interpretation and are more separable. NullSpaceNet ensures that all input images that belong to the same class are collapsed into one point in this new joint-nullspace, and the input images of different classes are collapsed into different points with high separation margins. Moreover, a novel differentiable loss function is proposed that has a closed-form solution with no free parameters. NullSpaceNet architecture consists of two components; 1) a feature extractor backbone (i.e., the convolution and pooling layers), which is used to extract features from the input, and 2) a nullspace layer, which maps from the pixel-level image to the joint-nullspace. This novel architecture and formulation results in a significant reduction in the number of learnable parameters in the network. NullSpaceNet is architecture-agnostic, which means it can use any feature extractor as a backbone in its first component. NullSpaceNet exhibits superior performance when tested over four different datasets against VGG16, MobileNet-224, and MNASNET1-0. In general, NullSpaceNet needs only 1 – 30% of the time it takes a traditional CNN to classify a batch of images, and with better accuracy of up to +2.57%.

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-the-art performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness information from pre-trained networks that have been trained on the image classification task. Furthermore, the pre-trained Siamese architecture is sparsely activated by the category label which leads to unnecessary calculations and overfitting. In this paper, we propose to learn a Domain-Aware, that is fully utilizing semantic and objectness information while producing a class-agnostic using a ridge regression network. Moreover, to reduce the sparsity problem, we solve the ridge regression problem with a differentiable weighted-dynamic loss function. Our tracker, dubbed DomainSiam, improves the feature learning in the training phase and generalization capability to other domains. Extensive experiments are performed on five tracking benchmarks including OTB2013 and OTB2015 for a validation set; as well as the VOT2017, VOT2018, LaSOT, TrackingNet, and GOT10k for a testing set. DomainSiam achieves state-of-the-art performance on these benchmarks while running at 53 FPS.