To build such a model, we will use The Stanford Cars Dataset, an extensive collection of car images. It consists of 16,185 total images labeled with 196 classes based on the car's Make/Model/Year. An example of one of these classes is shown below. The dataset is split into training images and testing images (roughly 50–50% train-test split), and each car class has around 40 images in the training set and the same amount in the testing set as well. The dataset contained no missing values, so no data removal or imputations was required. A challenge was to automate the extraction cars' Make/Model/Year since strings varied in length and character type.

Sign in to report inappropriate content. Softnautics developed a software for Lattice which identifies vehicles and classifies them as heavy, light, and two-wheel. The inferencing is done using Convolutional Neural Networks implemented in the Embedded Vision Development Kit's ECP5 FPGA. Power consumption is less than 1W.

We investigate whether ResNet architectures can outperform more traditional Convolutional Neural Networks on the task of fine-grained vehicle classification. We train and test ResNet-18, ResNet-34 and ResNet-50 on the Comprehensive Cars dataset without pre-training on other datasets. We then modify the networks to use Spatially Weighted Pooling. Finally, we add a localisation step before the classification process, using a network based on ResNet-50. We find that using Spatially Weighted Pooling and localisation both improve classification accuracy of ResNet50. Our method achieves higher accuracy than a range of methods including those that use traditional CNNs. However, our method does not perform quite as well as pre-trained networks that use Spatially Weighted Pooling. Keywords: Vehicle recognition, Intelligent surveillance, ResNets 1. Introduction In the fine-grained vehicle classification problem, a class consists of both make and model attributes, with the optional addition of the year that a particular model version was released (e.g. If such a'year' attribute is required, the difficulty of the problem increases significantly, due to the similarity of updated models. This problem differs from more coarse recognition, which may categorise by vehicle type (car, van, bus, etc) and have far fewer classes. Several methods have been used to try and solve fine-grained vehicle classification. The main limitation of these approaches is the inability to differentiate between similar car models.

Classification and identification of moving vehicles from audio signals is of interest in many applications, ranging from traffic flow management to military target recognition. Classification may involve differentiating vehicles by type, such as jeep, sedan, etc. Identification can involve distinguishing specific vehicles, even within a given vehicle type. Since audio data is small compared to, say, video data, multiple audio sensors can be placed easily and inexpensively. However, there are certain obstacles having to do with both hardware and physics. Certain microphones and recording devices have built-in features, for example, damping/normalizing that may be applied when the recording exceeds a threshold.