Object Tracking through Residual and Dense LSTMs
This work addresses robustness in object tracking for applications like surveillance and robotics, but it is incremental as it builds on existing LSTM trackers with architectural modifications.
The paper tackled the problem of visual object tracking by enhancing LSTM-based trackers with residual and dense connections to improve robustness against appearance changes, occlusions, and out-of-view objects, showing that DenseLSTMs outperform other variants in experiments on the Re3 tracker.
Visual object tracking task is constantly gaining importance in several fields of application as traffic monitoring, robotics, and surveillance, to name a few. Dealing with changes in the appearance of the tracked object is paramount to achieve high tracking accuracy, and is usually achieved by continually learning features. Recently, deep learning-based trackers based on LSTMs (Long Short-Term Memory) recurrent neural networks have emerged as a powerful alternative, bypassing the need to retrain the feature extraction in an online fashion. Inspired by the success of residual and dense networks in image recognition, we propose here to enhance the capabilities of hybrid trackers using residual and/or dense LSTMs. By introducing skip connections, it is possible to increase the depth of the architecture while ensuring a fast convergence. Experimental results on the Re3 tracker show that DenseLSTMs outperform Residual and regular LSTM, and offer a higher resilience to nuisances such as occlusions and out-of-view objects. Our case study supports the adoption of residual-based RNNs for enhancing the robustness of other trackers.