Classes
struct	CelanturDetection
	Structure to hold information about a detection made by the Celantur SDK. More...

class	ModelCompileException
	Exception class for errors during model compilation. This exception is thrown when there are issues encountered while compiling a machine learning model. More...

class	ModelLoadException
	Exception class for errors during model loading. This exception is thrown when there are issues encountered while loading a machine learning model. More...

class	DimensionMismatchException
	Exception class for dimension mismatches. This exception is thrown when there is a mismatch in expected dimensions, such as input size or tensor shapes. More...

struct	DetectionProcessingConfig
	Configuration that describes processing of a particular class This structure contains the type of blurring to be applied to detections of a specific class. More...

struct	ProcessorParams
	Structure to hold parameters for the image processor. This structure contains various settings for configuring the image processing. More...

struct	ImageMetadata
	Metadata associated with an image or frame. for now, just a placeholder. More...

struct	FrameMetadata
	Metadata associated with a video frame. for now, just a placeholder. More...

struct	MatContainer
	Container for an image and its associated metadata. for now, just a placeholder. More...

struct	ModelThresholds
	Structure to hold model threshold values for different object classes. This structure contains threshold values for detecting faces, license plates, persons, and vehicles. Class ids are identical to the celantur container. More...

struct	CPUInfo
	Structure to hold CPU information. More...

struct	Dims
	Structure to hold dimensions information. This structure contains the name, number of dimensions, dimension sizes, and whether it is an input dimension. More...

struct	ExifMetadata
	Structure to manage EXIF metadata for images. This structure encapsulates EXIF data and provides methods to manipulate and retrieve information from it. It is used in conjunction with JPEG encoding and decoding functions to preserve image metadata. More...

Typedefs
typedef DimensionMismatchException	dimension_mismatch_exception
	Alias for backward compatibility. More...

typedef std::map< CelanturClassId, DetectionProcessingConfig >	PerTypeProcessingConfig
	Configuration map for processing different detection types. This map associates each CelanturClassId with its corresponding DetectionProcessingConfig, allowing for fine-tuned processing settings based on the type of detection. More...

typedef std::tuple< int, int, int >	MinOptMaxDims
	A tuple representing minimum, optimal, and maximum dimensions. This tuple is used to specify the range of dimensions for model optimization. The three integers represent the minimum, optimal, and maximum dimensions respectively. More...

typedef std::map< std::string, std::any >	InferenceEnginePluginSettings
	The settings for the inference engine used during runtime. The settings are passed as a map of key-value pairs. More...

typedef std::map< std::string, std::any >	InferenceEnginePluginCompileSettings
	The settings for compiling the model for the inference engine. The settings are passed as a map of key-value pairs. More...

Enumerations
enum class	BlurType { None = 0 , BBox_Oval = 1 , BBox_Rectangle = 2 , Segmentation = 3 }
	Enum to describe the blur in celantur::DetectionProcessingConfig. More...

enum class	CelanturClassId { LicensePlate = 101 , Person = 102 , Face = 103 , Vehicle = 104 }
	Class ids enum that is used in celantur::CelanturDetection and celantur::DetectionProcessingConfig to describe detection class Class ids are identical to the celantur container. More...

enum class	Rotation { None = 0 , Rotated90Clockwise = 1 , Rotated180 = 2 , Rotated90CounterClockwise = 3 }
	Enum to represent image rotation states. is used in celantur::FrameMetadata to describe the rotation of the frame. More...

enum class	OptimisationLevel { Low , Medium , Full }
	Enumeration for different levels of optimization. This enum is used to specify the desired level of optimization during model compilation. More...

enum class	CompilePrecision { FP32 , FP16 , INT8 }
	Enumeration for different precision levels during model compilation. This enum is used to specify the desired precision for model weights and computations. Most engines support only FP32. Currently, only TensorRT supports FP16. INT8 is supported by TensorRT and OpenVINO, but requires special model provided to you by Celantur. More...

enum class	LogSeverity { Error , Warning , Debug }
	Enumeration for different log severity levels. More...

Functions
const PerTypeProcessingConfig	DEFAULT_PER_TYPE_PROCESSING_CONFIG ({ {CelanturClassId::LicensePlate, DetectionProcessingConfig{ BlurType::BBox_Rectangle, 0.3f, 0.0f, 1.0f, true }}, {CelanturClassId::Person, {BlurType::None}}, {CelanturClassId::Face, { BlurType::BBox_Oval, 0.3f, 0.0f, 0.2f, true }}, {CelanturClassId::Vehicle, {BlurType::None}}, })
	Default per-type processing configuration. More...

CPUInfo	get_cpu_info ()
	Function to retrieve CPU information. More...

void	serialise_image_metrics_to_json (cv::Mat image, std::vector< CelanturDetection > detections, std::string image_name, std::string input_folder, std::ostream &os)
	serialise detections to JSON format. Is identical to the celantur-container functionality. More...

std::vector< CelanturDetection >	filter_detections_by_threshold (const std::vector< CelanturDetection > &detections, const ModelThresholds &thresholds)
	Filter detections based on confidence thresholds for different object classes. This function takes a vector of CelanturDetection objects and filters them according to the specified thresholds for each class. More...

std::vector< CelanturDetection >	filter_detections_by_class_name (const std::vector< CelanturDetection > &detections, const std::set< std::string > &classes)
	Filter detections based on a set of class names. This function takes a vector of CelanturDetection objects and filters them to include only those whose class names are present in the provided set. More...

std::vector< CelanturDetection >	filter_detections_by_class (const std::vector< CelanturDetection > &detections, const std::set< CelanturClassId > &classes)
	Filter detections by type. This function takes a vector of CelanturDetection objects and filters them to include only those whose class IDs are present in the provided set. More...

cv::Mat	visualise_detections (const cv::Mat image, std::vector< CelanturDetection > detections)
	Visualise detections on an image. This function takes an input image and a vector of CelanturDetection objects, and draws bounding boxes and class labels on the image to visualize the detections. Can be used for debug purposes. More...

std::vector< unsigned char >	jpeg_encode (cv::Mat image, int jpeg_quality=95, std::optional< ExifMetadata > exif_metadata=std::nullopt)
	Encode an image to JPEG format with optional EXIF metadata. This function compresses the input image to JPEG format, allowing specification of JPEG quality and embedding of EXIF metadata if provided. More...

cv::Mat	jpeg_decode (const unsigned char *data, size_t size)
	Decode a JPEG image from a byte array. This function takes a byte array containing JPEG-encoded data and decodes it into an OpenCV cv::Mat image. More...

cv::Mat	jpeg_decode (std::vector< unsigned char > data)
	Decode a JPEG image from a vector of bytes. More...

ExifMetadata	jpeg_get_exif_metadata (const unsigned char *data, size_t size)
	Extract EXIF metadata from a JPEG byte array. This function parses the EXIF metadata from a JPEG image provided as a byte array and returns it as an ExifMetadata object. More...

cv::Mat	rotate_image (const cv::Mat &image, int orientation)
	Rotate an image based on EXIF orientation. This function rotates the input image according to the specified EXIF orientation value, ensuring correct display orientation. More...

Classes

Typedefs

Enumerations

Functions